ml-agents

作者	SHA1	备注	提交日期
Deric Pang	20dd50c4	Addressing feedback from offline meeting. - python directory has been removed. - config dirctory created. - mlagents-learn now takes --env as an optional arg.	6 年前
GitHub	3900ed66	Merge pull request #1083 from Unity-Technologies/develop-flat-code-restructure ML-Agents Code Restructure	6 年前
GitHub	10d2a19d	Release v0.5 (Develop) (#1203 )	6 年前
GitHub	f8df71a0	Revert "Release v0.5 (Develop) (#1203 )" (#1222 ) This reverts commit 448aac65dc891bad04a23a02d275f6a1d2704e1e.	6 年前
GitHub	29084e77	Curriculum learning reward thresholding bug fix (#1141 )	6 年前
GitHub	ab6eb8dc	Fix TF Nan bug (#1178 ) * Fix for TF NaNs * New soccer model	6 年前
GitHub	63062b92	updated the Pyramids model (#1184 ) * updated the Pyramids model * updated the pyramids model, chnaged the max_steps to reflect the new max steps required to achive ~1.8 cumulative reward	6 年前
GitHub	50228570	updated the walljump model for the multi-discrete action space (#1198 )	6 年前
GitHub	25495874	Merge pull request #1223 from Unity-Technologies/release-v0.5 Release v0.5	6 年前
GitHub	560f1bd7	Merge pull request #1224 from Unity-Technologies/release-v0.5 Release v0.5	6 年前
GitHub	3c9603d6	Demonstration Recorder (#1240 )	6 年前
Arthur Juliani	18cea1f2	Put Time Horizon back into the default training config for BC (#1291 ) Put Time Horizon back into the default training config for BC	6 年前
GitHub	bcd487a1	Develop environment bc fix and doc update (#1317 ) * split the config into two files * fixed the Training-ML-Agents.md doc * added the configs for all of the IL scenes	6 年前
GitHub	f99dc261	Rename brains to new names (#1321 )	6 年前
vincentpierre	b5edc64a	typos in the config	6 年前
Arthur Juliani	107d734e	New model for the dynamic crawler (#1322 ) * New model for the dynamic crawler * Added Dynamic Crawler to yaml * Attatch model to brain * Remove unneeded player brain	6 年前
GitHub	285d33c7	Fix brain name (#1349 )	6 年前
vincentpierre	5c060417	Added PushBlock models, fixed trainer config and fixed Learning brain asset (#1344 ) * Added PushBlock models, fixed trainer config and fixed Learning brain asset * Fixed PushBlock model to be in correct place * Added BananaLearning, deleted bytes files for PushBlock, fixed PushBlockLearning.asset * Deleted stray file * Added WallJumpArea training mods * Fixed Banana collector	6 年前
Arthur Juliani	59126c8c	Release v0.6 tennis (#1350 ) * Modified the scene, missing the model * modified the hyperparameters * Updated the model	6 年前
vincentpierre	6843dac6	Release v0.6 marwan tf (#1351 ) * Adding model for 3D Balance Ball. * Adding LearningBrain to BroadCast Hub. * Removed CrawlerPlayer Brain * Renamed CrawlerLearning —> CrawlerStaticLearning * Update Hallway models * Attaching model to brain for Hallway * Attaching model to 3DBall Brain. * Updated CrawlerLearning —> CrawlerStaticLearning on trainer config. * Adding Reacher model * Remove model specification in Hallway Brain asset * Removing model specification from 3Dball scene * Adding crawler model file * Specifying learning brain as default for crawler	6 年前
vincentpierre	148bd304	updated the models for the soccer, gridworld and 3dballhard (#1328 ) * updated the models for the soccer, gridworld and 3dballhard * updated the 3dball hard model * updated the soccer model	6 年前
GitHub	547f0e98	Merge pull request #1361 from Unity-Technologies/release-v0.6 Merge Release v0.6 into develop	6 年前
GitHub	8c7c62f0	Doc clarification and typo fix for offline BC (#1481 ) Clarified run command in offline BC doc. Also removed the Demon from the offline BC config yaml.	6 年前
GitHub	c8cc5a29	Merge pull request #1495 from Unity-Technologies/release-v0.6 release-v0.6 --> develop	6 年前
GitHub	a196dde2	Merge pull request #1494 from Unity-Technologies/release-v0.6 v0.6 Release	6 年前
Jonathan Harper	603485bd	Update curricula brain names for 0.6 As of v0.6, the WallJump example has new brain names while PushBlock doesn't support curriculum learning. This change renames the WallJump curriculum files and removes the PushBlock files.	6 年前
GitHub	8b1f0a38	Merge pull request #1589 from Unity-Technologies/hotfix-0.6.0a Hotfix 0.6.0a to develop	6 年前
GitHub	c0c289cc	Merge pull request #1588 from Unity-Technologies/hotfix-0.6.0a Hotfix 0.6.0a to master	6 年前
GitHub	610b8852	Release v0.8.2 update models (#2178 ) * ignore the idea file * Retrained most of the models * Updated the remaining models	5 年前
GitHub	d5f6b7f8	Merge pull request #2157 from Unity-Technologies/release-v0.8.2 Release v0.8.2	5 年前
GitHub	dcef9f69	Merge pull request #2179 from Unity-Technologies/release-v0.8.2 Merge from release 0.8.2 to develop	5 年前
GitHub	40c7fc48	Merge branch 'develop' into protobuf_update	5 年前
GitHub	4ac79742	Refactor reward signals into separate class (#2144 ) * Create new class (RewardSignal) that represents a reward signal. * Add value heads for each reward signal in the PPO model. * Make summaries agnostic to the type of reward signals, and log weighted rewards per reward signal. * Move extrinsic and curiosity rewards into this new structure. * Allow defining multiple reward signals in YAML file. Add documentation for this new structure.	5 年前
GitHub	be4292fb	Add different types of visual encoder (nature cnn/resnet) Add resnet and nature cnn in addition to default visual encoder	5 年前
GitHub	6a212f73	Improvements for GAIL (#2296 ) * Don't 0 value bootstrap for GAIL and Curiosity * Add gradient penalties to GAN to help with stability * Add gail_config.yaml with GAIL examples * Cleaned up trainer_config.yaml and unnecessary gammas * Documentation updates * Code cleanup	5 年前
Ervin T	a46f3faa	Enable generalization training (#2232 ) * Add Sampler and SamplerManager * Enable resampling of reset parameters during training * Documentation for Sampler and example YAML configuration file	5 年前
Ervin T	ca32cadf	Fix default for vis_encode_type (#2330 )	5 年前
Ervin T	00a3b592	Fix docs for Generalization (#2334 ) * Fix naming conventions for consistency * Add generalization link to ML-Agents Overview * Add generalization to main Readme * Include types of samplers available for use	5 年前
GitHub	4991d83f	Merge pull request #2346 from Unity-Technologies/release-0.9.0 Merge latest fixes from release into develop	5 年前
GitHub	53475207	Merge pull request #2380 from Unity-Technologies/release-0.9.0 Release v0.9.0	5 年前
sankalp04	34127b76	Example parameter sampling file config	5 年前
GitHub	6a81a2f4	Add Soft Actor-Critic as trainer option (#2341 ) * Add Soft Actor-Critic model, trainer, and policy and sac_trainer_config.yaml * Add documentation for SAC and tweak PPO documentation to reference the new pages. * Add tests for SAC, change simple_rl test to run both PPO and SAC.	5 年前
Ervin Teng	b1bfb9e8	Delete VisualBanana	5 年前
GitHub	36528481	Merge pull request #2522 from Unity-Technologies/develop-cleanupconfig Clean up SAC config	5 年前
Yuan Gao	0c42db82	Update the offline_bc_config path	5 年前
GitHub	d80812be	Merge pull request #2526 from Unity-Technologies/develop-update-offline-bc Update the offline_bc_config path	5 年前
GitHub	3df585d9	Fix issue where SAC encoder type is always simple (#2548 )	5 年前
GitHub	3683cc1c	Enable learning rate decay to be disabled (#2567 )	5 年前
GitHub	bebdb293	ML-Agents Branding & Color Updates (#2583 ) * new env styles rebased on develop * added new trained models * renamed food collector platforms * reduce training timescale on WallJump from 100 to 10 * uncheck academy control on walljump * new banner image * rename banner file * new example env images * add foodCollector image * change Banana to FoodCollector and update image * change bouncer description to include green cube * update image * update gridworld image * cleanup prefab names and tags * updated soccer env to reference purple agent instead of red * remove unused mats * rename files * remove more unused tags * update image * change platform to agent cube * update text. change platform to agents head * cleanup * cleaned up weird unused meta files * add new wall jump nn files and rename a prefab * walker change stacked states from 5 to 1 walker collects physics observations so stacked states are not need...	5 年前
GitHub	aa861bef	Improved SAC hyperparameters for Crawler, Walker (#2635 ) * Tweak SAC hyperparams * Make network bigger * Properly report entropy * Revert "Properly report entropy" This reverts commit 383a8d8f1d60ee0ef4ffd87a59aa08d974616d4e.	5 年前
GitHub	b2fa2268	Merge pull request #2648 from Unity-Technologies/release-0.10.0 Release 0.10.0	5 年前
GitHub	d1ebca5c	Merge pull request #2649 from Unity-Technologies/release-0.10.0 Merge Release 0.10.0 back to develop	5 年前
Vilmantas Balasevicius	2d032594	Further modifications to make PPO work	5 年前
Anupam Bhatnagar	cc208c00	resolving conflicts	5 年前
GitHub	5f5ccfa0	Feature Deprecation : Online Behavioral Cloning (#2659 ) * Feature Deprecation : Online Behavioral Cloning In this PR : - Delete the online_bc_trainer - Delete the tests for online bc - delete the configuration file for online bc training * Deleting the BCTeacherHelper.cs Script TODO : - Remove usages in the scene - Documentation Edits DO NOT MERGE * IMPORTANT : REMOVED ALL IL SCENES - Removed all the IL scenes from the Examples folder * Removed all mentions of online BC training in the Documentation * Made a note in the Migrating.md doc about the removal of the Online BC feature.	5 年前
Ervin Teng	258b5d00	Remove unneeded beta param from SAC config	5 年前
GitHub	f22c41db	Merge pull request #2704 from Unity-Technologies/hotfix-0.10.1 Merge Hotfix 0.10.1	5 年前
Anupam Bhatnagar	b733b34c	resolving conflicts	5 年前
Chris Elion	a1967c19	Merge remote-tracking branch 'origin/develop' into try-tf2-support	5 年前
GitHub	7e68f08f	Merge Hotfix 0.10.1 to Develop (#2708 )	5 年前
Hunter	c92a9008	init	5 年前
Hunter	47d31907	added new nn files	5 年前
GitHub	c9b71cee	Better hyperparams for GridWorld/SAC (#2776 )	5 年前
Hunter	70e7a646	clean up config	5 年前
GitHub	99146e97	1 to 1 Brain to Agent (#2729 ) * 1 to 1 Brain to Agent This is a work in progess In this PR : - Deleted all Brain Objects - Moved the BrainParameters into the Agent - Gave the Agent a Heuristic method (see Balance Ball for example) - Modified the Communicator and ModelRunner : Put can only take one agent at a time - Made the IBrain Interface with RequestDecision and DecideAction method No changes made to Python [Design Doc](https://docs.google.com/document/d/1hBhBxZ9lepGF4H6fc6Hu6AW7UwOmnyX3trmgI3HpOmo/edit#) * Removing editorconfig * Updating BallanceBall scene * grammar mistake * Clearing the Agents of the Model runner * Added Documentation on IBrain * Modified comments on GiveModel * Introduced a factory * Split Learning Brain in two * Changes to walljump * Fixing the Unit tests * Renaming the Brain to Policy * Heuristic now has priority over training * Edited code comments * Fixing bugs * Develop one to one scene edits...	5 年前
Ervin Teng	776b6c8b	Add new trainer config for walljump	5 年前
Ervin Teng	cc299259	Adjust SAC params	5 年前
Hunter	7c1a38e0	add drawspheres gizmo to perception	5 年前
Hunter	90457de5	added builder env. observing blocks pos	5 年前
Hunter	8b55f522	more testing with high targets	5 年前
Chris Elion	3d8a70fb	Merge remote-tracking branch 'origin/develop' into try-tf2-support	5 年前
GitHub	495873e5	Merge pull request #2833 from Unity-Technologies/release-0.11.0 Release 0.11.0	5 年前
GitHub	72bab623	reduce max_steps for Gridworld (#2973 )	5 年前
Ervin Teng	58a4ea71	Increase max steps for 3DBall	5 年前
GitHub	cdf307bb	add BC FoodCollector config (#2987 )	5 年前
GitHub	a4c111f4	Merge pull request #3012 from Unity-Technologies/release-0.12.0-to-develop Release 0.12.0 to develop	5 年前
GitHub	d4780a55	Merge pull request #3010 from Unity-Technologies/release-0.12.0-to-master Merge Release 0.12.0 to master	5 年前
Ervin Teng	34f9577c	Merge branch 'develop' into develop-agentprocessor	5 年前
Ervin Teng	eb4a04a5	Merge branch 'master' into develop-tanhsquash	5 年前
GitHub	1fa07edb	Remove Standalone Offline BC Training (#2969 )	5 年前
GitHub	45c22d13	Run precommit in its own job, cache the data (#3094 )	5 年前
Andrew Cohen	082789ea	Merge branch 'master' into develop-magic-string	5 年前
Ervin Teng	1bd791e5	Merge branch 'master' into develop-agentprocessor	5 年前
GitHub	bec2e8f0	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113 )	5 年前
Andrew Cohen	c8514c18	Merge branch 'master' into develop-magic-string	5 年前
andrewcoh	317c59d2	Move FoodCollector to gail_config and remove offline_bc_config.yaml (#3170 ) * Move FoodCollector to gail_config	5 年前
GitHub	d985dded	Merge branch 'master' into merge-release-0.13.0	5 年前
GitHub	ad42705d	Merge pull request #3185 from Unity-Technologies/merge-release-0.13.0 Merge release 0.13.0	5 年前
GitHub	b0a2a54f	Add 'run-experiment' script, simpler curriculum config (#3186 ) This change adds a new 'mlagents-run-experiment' endpoint which accepts a single YAML/JSON file providing all of the information that mlagents-learn accepts via command-line arguments and file inputs. As part of this change the curriculum configuration is simplified to accept only a single file for all the curricula in an environment rather than a file for each behavior.	5 年前
Yuan Gao	0817c44b	Moved the demo files	5 年前
GitHub	b3d3a9d6	Merge pull request #3202 from Unity-Technologies/develop-move-demo Move the demo files into corresponding example/[env_name]/Demos/ folder	5 年前
Ervin Teng	98ed88b1	Merge branch 'master' into develop-separatevalue	5 年前
Ervin Teng	29f3330f	Merge master into hotfix-0.13.1	5 年前
GitHub	14193ada	Self-play for symmetric games (#3194 )	5 年前
GitHub	0ff8f9af	Create ML-Agents Package (#3267 ) Convert the UnitySDK to a Packman Package. - Separate Examples into a sample project. - Move core UnitySDK Code into com.unity.ml-agents. - Create asmdefs for the ml-agents package. - Add package validation tests for win/linux/max. - Update protobuf generation scripts. - Add Barracuda as a package dependency for ML-Agents. (users no longer have to install it themselves).	5 年前
Ervin Teng	db249ceb	Merge branch 'master' into develop-splitpolicyoptimizer	5 年前
Ervin Teng	9b0b2fed	Reduce memory sizes	5 年前
Ervin Teng	ab9b082a	Fix Hallway summary freq	5 年前
GitHub	6284ea4a	Reduce max steps for Bouncer, summary for Hallway (#3343 )	5 年前
GitHub	8eb8e279	Fix WallJump yaml indentation in docs and curriculum config (#3340 ) * Fix yaml indentation in Curriculum Learning docs * Fix yaml indentation in WallJump curriculum config	5 年前
GitHub	ae97ab3a	Soccer refactor (#3331 )	5 年前
GitHub	0d6fffc1	Reduce num steps for walljump (#3377 )	5 年前
Ervin Teng	d4ee7346	Merge commit 'f9c05a61d574305497789b5997f1ae3ea1b1ad3b' into develop-splitpolicyoptimizer	5 年前
GitHub	c1340b0e	Hotfix docs odd (#3379 ) * Updating version number (#3366) * updating version number * fixing version numbers * migration guide (#3375) * Reduce num steps for walljump (#3377) * Fixing the Docs on On Demand Decision Co-authored-by: Anupam Bhatnagar <anupambhatnagar@gmail.com> Co-authored-by: Chris Elion <celion@gmail.com> Co-authored-by: Ervin T. <ervin@unity3d.com>	5 年前
Ervin Teng	d2f67c50	Reduce num steps for walljump	5 年前
Andrew Cohen	23f74f21	soccer fives	5 年前
Andrew Cohen	5c7a1fbf	cloud run	5 年前
Andrew Cohen	7d90b042	soccerfives curricula	5 年前
Anupam Bhatnagar	d5617834	[bug-fix] Update the gail config for the new steps in 0.14.0 (#3475 )	5 年前
Anupam Bhatnagar	be7e2e3a	Fix demo path for pushblock (#3489 )	5 年前
Ervin Teng	5ef902bf	Merge branch 'master' into develop-splitpolicyoptimizer	5 年前
GitHub	5e78e5d4	[bug-fix] Update the gail config for the new steps in 0.14.0 (#3475 )	5 年前
GitHub	472f9f0e	Merge branch 'master' into develop-badEnvReturnCode	5 年前
Andrew Cohen	b7d77740	Merge branch 'master' into soccer-fives	5 年前
Ervin Teng	1859f252	Merge commit 'fbcdd83c087135f870e785cc72e5ff9a7e898e3a' into develop-splitpolicyoptimizer	5 年前
Andrew Cohen	39a76867	added more backward raycasts to twos and fives	5 年前
GitHub	3f8bbaf1	Fix demo path for pushblock (#3489 )	5 年前
GitHub	c145e75b	Split Policy and Optimizer, common Policy for PPO and SAC (#3345 )	5 年前
Andrew Cohen	5b0aca29	Merge branch 'master' into soccer-fives	5 年前
Andrew Cohen	4edb7f41	updated config/soccer brains	5 年前
Ervin Teng	1156b9b3	Merge branch 'develop-splitpolicyoptimizer' into develop-removeactionholder	5 年前
Ervin Teng	d57124b4	Merge 'master' into develop-removeactionholder	5 年前
Anupam Bhatnagar	e04fcd71	Merge branch 'master' into master-into-release-0.14.1	5 年前
Ervin Teng	d10d27e2	Merge commit '9450d3fc0dda4547a14c5ed1b7e13fc6e3a15413' into develop-nopreviousactions	5 年前
Andrew Cohen	30725c27	2v1 soccer config and env	5 年前
Ervin Teng	c825f13e	Reduce PushBlock max_steps	5 年前
Ervin Teng	c3ff4a31	Cut bouncer max steps	5 年前
Anupam Bhatnagar	21a526c5	[skip ci] shorter 3dball run	5 年前
GitHub	9d9c8a8a	Merge pull request #3576 from Unity-Technologies/develop-shortentrainerconfigs [change] Reduce max_steps for PushBlock and Bouncer	5 年前
GitHub	e3af96ca	Merge branch 'master' into develop-demo-load-seek	5 年前
Andrew Cohen	b1cfa74d	Merge branch 'master' into develop-test-imitation	5 年前
GitHub	0d3fd17e	[bug-fix] Increase 3dballhard and GAIL default steps (#3636 )	5 年前
Andrew Cohen	53bea15c	Merge branch 'master' into soccer-fives	5 年前
Andrew Cohen	ac261e36	Merge branch 'master' into self-play-mutex	5 年前
GitHub	4fa9735e	[bug-fix] Increase 3dballhard and GAIL default steps (#3636 ) (#3647 ) Co-authored-by: Ervin T <ervin@unity3d.com>	5 年前
Andrew Cohen	eefc4811	Merge branch 'master' into self-play-mutex	5 年前
GitHub	3a771afa	Rename Generalization -> Environment Parameter Randomization (#3646 ) * Rename generalization to Environment Parameter Randomization	5 年前
Andrew Cohen	072b4135	soccer 2v1 on the cloud	5 年前
Ervin Teng	84e526fa	Update trainer config	5 年前
Andrew Cohen	c70cfa63	running soccer for more steps	5 年前
Andrew Cohen	fb993986	Merge branch 'master' into self-play-mutex	5 年前
Andrew Cohen	b42c9482	Merge branch 'self-play-mutex' into soccer-2v1	5 年前
Andrew Cohen	5d21e211	tennis config	5 年前
Andrew Cohen	a13f107f	updated self-play doc for asymmetric games/changed current_self->current_best	5 年前
Andrew Cohen	f7e76054	tennis config restored	5 年前
Andrew Cohen	6e43bbf4	soccer config	5 年前
Andrew Cohen	bc611906	removed team-change CLI	5 年前
Andrew Cohen	42518d84	Merge branch 'self-play-mutex' into soccer-2v1	5 年前
Andrew Cohen	650ec121	Merge branch 'self-play-mutex' into soccer-2v1	5 年前
Andrew Cohen	941b8ae7	Strikers vs goalie added	5 年前
Andrew Cohen	1ba1bc22	tennis config	5 年前
Andrew Cohen	345fa382	current_best_ratio -> latest_model_ratio	5 年前
Andrew Cohen	c7a34413	Merge branch 'self-play-mutex' into soccer-2v1	5 年前
Andrew Cohen	61d38b15	rerunning all self-play	5 年前
Andrew Cohen	d9f1a2f5	more experiments for self-play	5 年前
Andrew Cohen	d7b8cf16	CubeWars	5 年前
GitHub	9cbc3fa2	Asymmetric self-play (#3653 )	5 年前
Ervin Teng	06fa3d39	Merge branch 'master' into develop-sac-apex	5 年前
Anupam Bhatnagar	50e52d9c	Merge branch 'master' into distributed-training	5 年前
Andrew Cohen	72706301	soccer curriculum	5 年前
Andrew Cohen	c13259fd	curriculum for small soldiers	5 年前
Ervin Teng	b7151b51	Remove num_update as param	5 年前
Andrew Cohen	e91f5233	reduced steps cubewars	5 年前
Andrew Cohen	9fed4985	tennis curriculum	5 年前
bhh	35736d30	added scripts	5 年前
Andrew Cohen	e4f7f2a6	removed curriculum tennis	5 年前
Anupam Bhatnagar	d94ae012	[skip ci] shorter 3dball run	5 年前
Andrew Cohen	2e7f8f41	Merge branch 'develop-cubewars' into asymm-envs	5 年前
Andrew Cohen	a0985d94	increased striker goalie steps	5 年前
bhh	dc9fcd46	loosened joints retrained looking good	5 年前
Anupam Bhatnagar	06a54ae8	step increment moved to _update_policy, fixed exit status issue	5 年前
Anupam Bhatnagar	5d180caf	[skip ci] modify learning rate in horovod optimizer	5 年前
bhh	1ecc8924	final training done. ready to go.	5 年前
GitHub	aae58330	Merge branch 'master' into develop-add-inference-examples	5 年前
Ervin Teng	66bc2498	Trainer config adjustments	5 年前
Andrew Cohen	5a5e13fa	soccertwos config	5 年前
Anupam Bhatnagar	d49ceecc	[skip ci] moving summary writer to update_policy [skip ci] more fixes [skip ci] tweaking 3dball configs [skip ci] swap summary writer and step increment order	5 年前
bhh	9e40ed64	update config to 3.5M steps	5 年前
Andrew Cohen	44e6fa7b	soccer 1e8 timesteps/Tennis existential penalty	5 年前
Andrew Cohen	900ae050	new SoccerTwos brain	5 年前
Anupam Bhatnagar	86e16a64	[skip ci] tweaking 3dball configs	5 年前
Andrew Cohen	6f1f89f6	new soccertwos brain	5 年前
Hunter-Unity	2751b3a4	updated crawlerAgent code to match worm env	5 年前
Andrew Cohen	a90812a0	soccer twos for 50mill	5 年前
Ervin Teng	9b0da1a4	Adjust walker params	5 年前
Andrew Cohen	384f6439	reduced laser cd/increased heal	5 年前
Ervin Teng	0ff591bc	Adjust Reacher steps_per_update	5 年前
Ervin Teng	d11f2f73	Increase PushBlock summary steps	5 年前
GitHub	9695b89a	StrikerVsGoalie and SoccerTwos env improvements (#3699 )	5 年前
Arthur Juliani	c577ce26	Merge remote-tracking branch 'origin/master' into develop-add-fire	5 年前
Andrew Cohen	34349a2f	reduce latest_model prob	5 年前
Andrew Cohen	72bd2c5d	Merge branch 'soccer-2v1' into asymm-envs	5 年前
Andrew Cohen	8431ecb5	tennis reward fix	5 年前
Andrew Cohen	1ac4dfb3	update Tennis max step	5 年前
GitHub	4d23200b	[refactor] Run Trainers in separate threads (#3690 )	5 年前
Ervin Teng	9cd2c034	Merge branch 'master' of github.com:Unity-Technologies/ml-agents into develop-sac-apex	5 年前
Andrew Cohen	9b552f08	increased latest_model soccer prob	5 年前
Andrew Cohen	3daff010	svg config	5 年前
Andrew Cohen	47548ee4	tennis curriculum	5 年前
Andrew Cohen	79276531	new goalie	5 年前
Andrew Cohen	3bd33889	Merge branch 'soccer-2v1' into asymm-envs	5 年前
Andrew Cohen	e5c62cb8	update striker vs goalie brain/retrain	5 年前
Andrew Cohen	d2cf07be	increased tennis xurriculum	5 年前
Andrew Cohen	1d020fa7	Merge branch 'soccer-2v1' into asymm-envs	5 年前
Andrew Cohen	064bcdad	Merge branch 'soccer-2v1' into asymm-envs	5 年前
GitHub	f8909ab1	Add New 3 Joint Ragdoll Worm Environment (#3798 ) Co-authored-by: Arthur Juliani <awjuliani@gmail.com>	5 年前
Andrew Cohen	d54fdfbf	increase batch/buff/erbeta	5 年前
Andrew Cohen	028a8d59	larger network/6 stacked obs	5 年前
Andrew Cohen	ca6cdff3	fixed broken prefab...	5 年前
Andrew Cohen	32f562d9	striker goalie increase latest_mod ratio	5 年前
Andrew Cohen	3df4f4a3	smaller window cubewar	5 年前
Andrew Cohen	717fae65	reduce tennis latest_model_ratio	5 年前
Andrew Cohen	1c4ba1a5	add timestep bonus to loss	5 年前
Andrew Cohen	a1143427	increased entro bonus tennis	5 年前
Andrew Cohen	e9f570aa	slightly larger beta tennis	5 年前
Andrew Cohen	3f806353	increased beta	5 年前
Andrew Cohen	54972202	tuning beta tennis	5 年前
Andrew Cohen	0871fc96	remove beta/no curr tennis	5 年前
Andrew Cohen	547f3192	beta .05	5 年前
Arthur Juliani	212e2d1d	Merge remote-tracking branch 'origin/master' into develop-add-fire	5 年前
Andrew Cohen	04ac54a3	reduced tennis time horizon	5 年前
GitHub	f86fc81d	[refactor] Move configuration files to single YAML file (#3791 )	5 年前
Andrew Cohen	a5ca5e0c	reduce beta for new reward func	5 年前
Andrew Cohen	fda39c3d	more beta tuning...	5 年前
GitHub	2f80dd02	Worm SAC configs (#3912 )	5 年前
GitHub	98d4d5be	Add worm config for SAC (#3879 )	5 年前
Andrew Cohen	e3f6c716	higher granularity curr	5 年前
Andrew Cohen	39e0bbe9	remove debug log	5 年前
Andrew Cohen	1c2e1d79	increase beta	5 年前
Andrew Cohen	e7922b68	trying larger beta	5 年前
Andrew Cohen	376af981	lower agent height	5 年前
Andrew Cohen	14df5d02	increase gamma	5 年前
Andrew Cohen	052f1c87	reduce gamma	5 年前
Andrew Cohen	8fba6faa	increase network capacity	5 年前
Andrew Cohen	bbc1014a	reduce learning rate	5 年前
Andrew Cohen	d5428487	addforce and static walls	5 年前
Chris Elion	68b68396	Merge remote-tracking branch 'origin/master' into release_1_to_master	5 年前
Andrew Cohen	8ef0b3a8	opponent observations	5 年前
Chris Elion	ff7318c2	Merge remote-tracking branch 'origin/master' into release_1_to_master	5 年前
vincentpierre	c34dd5b6	Merge branch 'master' into develop-gym-wrapper	5 年前
Andrew Cohen	b6784390	frequent swapping of diverse opponents tennis	5 年前
Andrew Cohen	69acdeec	fixed reset tennis	5 年前
Andrew Cohen	a2f8319a	Merge branch 'master' into asymm-envs	5 年前
Andrew Cohen	d9d6c172	remove threading	5 年前
Arthur Juliani	89ad3020	Merge remote-tracking branch 'origin/master' into develop-add-fire # Conflicts: # ml-agents/mlagents/trainers/policy/tf_policy.py	5 年前
Hunter-Unity	e891d9b5	about to implement orientation cube	5 年前
Andrew Cohen	f74ac6ae	remove rotation hindrance	5 年前
Andrew Cohen	d7c2c163	please no more	5 年前
Andrew Cohen	a926aa7a	remove threaded	5 年前
Hunter-Unity	3edca8d0	reduced maxAngVel, enabled enhanced determinism, cont spec	5 年前
Andrew Cohen	d52168e9	threaded false	5 年前
Andrew Cohen	3f7f9883	remove thread	5 年前
Andrew Cohen	de2ca11b	no thread config	5 年前
Andrew Cohen	c5ce18c7	remove x/y vel, smaller network	5 年前
Hunter-Unity	0b02b434	added new dynamic nn file	5 年前
Andrew Cohen	fd7ee405	normalize by hand	5 年前
Hunter-Unity	9e20feef	hip facing reward	5 年前
Hunter-Unity	cb8eec30	Create WalkerDynamic.yaml	5 年前
Andrew Cohen	e58a3f5e	small swap	5 年前
Andrew Cohen	f21304a9	ball	5 年前
GitHub	c0d96ecd	Increase 3DBall generalization sampling interval (#3995 ) * increase sampling interval to 2000 * bring it up to 5000	5 年前
Andrew Cohen	fa66e9e9	beta.005	5 年前
Ervin Teng	f214836a	Changes for speed test	4 年前
Hunter-Unity	da6d25c9	updated walker dynamic demo file. cleanup	5 年前
Andrew Cohen	c3fd56b5	testing beta	5 年前
Andrew Cohen	13c2a209	added opp, decay eps removed	5 年前
Andrew Cohen	53f2f360	long tennis/soccer runs	5 年前
Hunter-Unity	99eadde6	try 100M steps on walkerdynamic	5 年前
Andrew Cohen	a89d9791	changed striker vs goalie config	5 年前
Hunter-Unity	c9821f85	100M steps	5 年前
Andrew Cohen	5dfa0014	increased beta for all self-play	5 年前
Hunter-Unity	07266f46	add dir vector obsv	5 年前
Hunter-Unity	f4c8f344	2e7 steps	5 年前
Andrew Cohen	59a60c1e	Merge branch 'master' into asymm-envs	5 年前
Hunter-Unity	ffa4ce52	testing bigger batch size	5 年前
GitHub	e92b4f88	[refactor] Structure configuration files into classes (#3936 )	4 年前
Hunter-Unity	85958dad	try 8x mem for cloud	5 年前
Andrew Cohen	11815554	revert soccer hyper params	5 年前
Hunter-Unity	b06dd988	8x batch size for cloud test	5 年前
Andrew Cohen	3c2ce7be	beta...	5 年前
Hunter-Unity	6b92b01a	epoch 10	5 年前
Andrew Cohen	a0dc8789	test new sampling method	4 年前
Hunter-Unity	e032db74	hyptest	5 年前
Andrew Cohen	4083e344	tennis window 10	5 年前
Andrew Cohen	46654d49	soccer 100	5 年前
Hunter-Unity	f17b1075	increase timescale for cloudtraining	5 年前
Andrew Cohen	bc249921	riker goalie 100	5 年前
HH	ad90e6b9	about to implement orientation cube	4 年前
Hunter-Unity	769dbec5	cp	4 年前
Andrew Cohen	4671cf17	tnenis congif	5 年前
Hunter-Unity	b3bf1418	try new cluster	4 年前
Andrew Cohen	78744111	test ghost	5 年前
Hunter-Unity	a3f7b980	cp	4 年前
Andrew Cohen	5f8ef3ca	.5 opponent tennis	5 年前
Andrew Cohen	4464ca46	ignoring commit checks	4 年前
Hunter-Unity	aca47e1f	200k buff cloud	4 年前
Andrew Cohen	20d973c8	bug	5 年前
Andrew Cohen	91217b0d	use settings.py to check PR config	4 年前
Andrew Cohen	4e4cf9e2	.5	5 年前
Chris Elion	20b5a157	update scenes and get them training	4 年前
Hunter-Unity	32feefee	update configs	4 年前
Andrew Cohen	53d1a98d	more entro	5 年前
Andrew Cohen	b6b2c58e	smaller window	5 年前
GitHub	8566ed4f	[bug-fix] Fix hyperparameters for Walker-SAC and WallJump-SAC (#4049 )	4 年前
Andrew Cohen	6568158f	3.o beta	5 年前
Andrew Cohen	b6d9c58b	beta 2	5 年前
HH	f7e650a6	reduced maxAngVel, enabled enhanced determinism, cont spec	4 年前
Andrew Cohen	bca3bd73	return to team change	5 年前
Andrew Cohen	4b8db5c3	test failure	5 年前
Andrew Cohen	55bafe1b	control	5 年前
Andrew Cohen	e7750fc9	Merge branch 'master' into develop-sampler-refactor	4 年前
GitHub	91f199cd	Self play hyperparameter improvements (#4063 )	4 年前
Andrew Cohen	6071c74f	hard reset on team change	5 年前
Andrew Cohen	922136f3	usual tennis	5 年前
GitHub	ee1098d1	[refactor] Improve config upgrade script and add test (#4056 )	4 年前
Andrew Cohen	55e3e7f6	sanity check	5 年前
Andrew Cohen	af364ac9	more exsp	5 年前
GitHub	101a8e00	Add Dynamic Walker. Improved Ragdoll Stability/Performance (#4037 ) * about to implement orientation cube * oCube spawining works. ready to train * working. about to try com * ready for training * add random rot on episode start * feet now alternate but runs backwards * still running with right leg in front * increased joint strength to 40k * removed texture example * reduced maxAngVel, enabled enhanced determinism, cont spec * rebuilt walker ragdoll to scale 1 * rebuilt ragdoll ready * update walker pair prefab * fixed bp heirarchy * added trained model, renamed scene, usecollisioncallbacks * updated dynamic platforms * added dynamic walker tf file. max speed 5 * DynamicWalker working. has working nn file * collect local rotations * added new dynamic nn file * hip facing reward * Create WalkerDynamic.yaml * fix hip rotation * about to clean up code * added dirIndicator and orentCubeGizmo * clean up * clea...	4 年前
Andrew Cohen	d91a7cbd	reduce time horizon tennis	5 年前
HH	8bee075b	added new dynamic nn file	4 年前
HH	5bf43487	hip facing reward	4 年前
HH	de87c750	Create WalkerDynamic.yaml	4 年前
Andrew Cohen	446bdeee	hund	5 年前
Andrew Cohen	4ba0d98c	cubewar and tennis stability test	5 年前
Andrew Cohen	bd1d6c08	all self-play	5 年前
Andrew Cohen	c0f7052b	Merge branch 'master' into develop-sampler-refactor	4 年前
Andrew Cohen	150e7d73	cubewar threaded false	5 年前
Andrew Cohen	34ecc7e6	Merge branch 'master' into asymm-envs	5 年前
Andrew Cohen	33458d24	running cubewar	5 年前
HH	2d2844bd	updated walker dynamic demo file. cleanup	4 年前
GitHub	a1c63c4b	Release 3 Cherry-pick bug-fixes and doc changes from master (#4102 ) * [bug-fix] Fix regression in --initialize-from feature (#4086) * Fixed text in GettingStarted page specifying the logdir for tensorboard. Before it was in a directory summaries which no longer existed. Results are now saved to the results dir. (#4085) * [refactor] Remove nonfunctional `output_path` option from TrainerSettings (#4087) * Reverting bug introduced in #4071 (#4101) Co-authored-by: Scott <Scott.m.jordan91@gmail.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
GitHub	8a49e8e0	[refactor] Remove nonfunctional `output_path` option from TrainerSettings (#4087 )	4 年前
Andrew Cohen	34f3ac64	updated cube war	5 年前
HH	d7e8c5e4	try 100M steps on walkerdynamic	4 年前
HH	8f463c55	100M steps	4 年前
Andrew Cohen	81cc5f69	reduce epsilon tennis ppo	5 年前
HH	005f377a	add dir vector obsv	4 年前
Anupam Bhatnagar	4afd8f92	first commit	4 年前
Andrew Cohen	45293f01	larger batch size	5 年前
HH	999fc7ab	2e7 steps	4 年前
Andrew Cohen	c68e865b	opp	5 年前
Andrew Cohen	03eef40b	constrain x tennis	5 年前
HH	f8a22591	testing bigger batch size	4 年前
HH	ef3be52c	try 8x mem for cloud	4 年前
HH	25d7ba5e	8x batch size for cloud test	4 年前
Andrew Cohen	0c17dc1b	cannot hit scenery tennis	5 年前
HH	2cce3bbe	epoch 10	4 年前
HH	90c7d05f	hyptest	4 年前
Andrew Cohen	31a5b2ee	4096 batch	5 年前
GitHub	5b0a5b9b	Moving domain randomization to C# (#4065 )	4 年前
Andrew Cohen	71d7c24b	0.0 latest model	5 年前
Arthur Juliani	9724c9ac	Merge master	4 年前
HH	f7dd600f	increase timescale for cloudtraining	4 年前
Andrew Cohen	346a90ba	move agent back	5 年前
HH	65b80abb	cp	4 年前
yanchaosun	3ef4196e	Added the algorithm named ppo_transfer	4 年前
HH	fa937cb9	try new cluster	4 年前
yanchaosun	c2d6f5c0	basic implementation	4 年前
HH	ba835a22	cp	4 年前
HH	ad2e63d6	200k buff cloud	4 年前
GitHub	ca3bdbc0	Fix 3DBall and 3DBallHard SAC regressions (#4132 )	4 年前
Andrew Cohen	8c0b3548	reduce batch size Tennis	4 年前
HH	48d78ac7	update configs	4 年前
Anupam Bhatnagar	24d5f881	first commit	4 年前
yanchaosun	ac4c80c2	integrate the implementation and hyperparameters	4 年前
HH	a121795d	Merge branch 'hh/develop/dynamic-walker' of https://github.com/Unity-Technologies/ml-agents into hh/develop/dynamic-walker	4 年前
yanchaosun	1e52ad3d	ready for cloud training	4 年前
HH	ced14d9d	update configs to new class format	4 年前
yanchaosun	e338ab91	test cloud training	4 年前
yanchaosun	f0881a94	fix commands for cloud training	4 年前
yanchaosun	05a96355	remove slim package	4 年前
Andrew Cohen	1f305f23	no latest model	5 年前
Jonathan Harper	4e7a1170	Adding training configs	4 年前
yanchaosun	44fa16fa	fix issues with cloud training	4 年前
Jonathan Harper	7656f419	More experimentation	4 年前
yanchaosun	ad95032b	transfer path	4 年前
GitHub	a28e2767	Update add-fire to latest master, including Policy refactor (#4263 ) * Update Dockerfile * Separate send environment data from reset (#4128) * Fixed a typo on ML-Agents-Overview.md (#4130) Fixed redundant "to" word from the sentence since it is probably a typo in document. * Updated the badge’s link to point to the newest doc version * Replaced all of the doc to release_3_doc * Fix 3DBall and 3DBallHard SAC regressions (#4132) * Move memory validation to settings * Update docs * Add settings test * Update to release_3 in installation.md (#4144) * rename to SideChannelManager +backcompat (#4137) * Remove comment about logo with --help (#4148) * [bugfix] Make FoodCollector heuristic playable (#4147) * Make FoodCollector heuristic playable * Update changelog * script to check for old release links and references (#4153) * Remove package validation suite from Project (#4146) * RayPerceptionSensor: handle empty and invalid tags (#4155...	4 年前
yanchaosun	b10b0895	test crawler	4 年前
yanchaosun	428f013e	add old crawler	4 年前
HH	9570a5fe	Delete trainer_config.yaml	4 年前
yanchaosun	59251abe	change yamls	4 年前
Andrew Cohen	4839e040	try team change zero	5 年前
Andrew Cohen	48f02b61	int as team change	5 年前
yanchaosun	cd1778ff	added one yaml	4 年前
Andrew Cohen	12bc2143	large window	5 年前
yanchaosun	a80915a8	yaml update	4 年前
Andrew Cohen	4f03be74	window 30	5 年前
yanchaosun	666c8ba9	new cloud training change	4 年前
Andrew Cohen	5efa1e92	time hor	5 年前
yanchaosun	59e93b0b	transfer config	4 年前
yanchaosun	d0714701	new setting for cloud	4 年前
Andrew Cohen	68c6d513	reduce time hor	5 年前
vincentpierre	599d7e9f	Merging master	4 年前
yanchaosun	d7402406	multiple sizes configs	4 年前
yanchaosun	5eccb4c9	new transfer test for cloud	4 年前
HH	5147f2c6	temp add robot arm training config	4 年前
yanchaosun	fe4e057f	test more configs	4 年前
HH	7afa1761	Merge branch 'master' into hh/develop/ragdoll-updates	4 年前
GitHub	1308b344	[CI] Better hyperparameters for Pyramids-SAC, WalkerStatic-SAC, and Reacher-PPO (#4154 )	4 年前
GitHub	8b913a96	Add TargetController/OrientationCubeController Components & Bugfix (#4157 ) * added Target and OCube controllers. updated crawler envs * update walker prefab * add refs to prefab * Update Crawler.prefab * update platform, ragdoll, ocube prefabs * reformat file * reformat files * fix behavior name * add final retrained crawler and walker nn files * collect hip ocube rot in world space * update crawler observations and update prefabs * change to 20M steps * update crwl prefab to 142 observ * update obsvs to 241. add expvel reward * change walkspeed to 3 * add new crawler and walker nn files * adjust rewards * enable other pairs * add RewardManager * cleanup about to do final training * cleanup add nn files for increased facing rew reduced height rew * try no facing rew * add vel only policy, try dy target * inc torq on cube * added dynamic cube nn. gonna try 40M steps * add 40M step test, more cleanup * ch...	4 年前
yanchaosun	d8d418c4	walker configs	4 年前
GitHub	559549e4	Add dynamics change to crawler (#4218 ) * update walker * add dynamics change crawler	4 年前
yanchaosun	7e3216ae	simple env test	4 年前
HH	84430eec	update config to match master	4 年前
GitHub	d42e82a8	Fix 3DBall PPO hard regression (#4133 )	4 年前
yanchaosun	cdaaa318	bisim	4 年前
yanchaosun	bc4b7f98	walker config	4 年前
yanchaosun	3d0d359c	bisimulation draft	4 年前
yanchaosun	1fdbfe65	no normalization	4 年前
yanchaosun	5a778ca3	fix normalization	4 年前
GitHub	8eefdcd3	Refactor of Curriculum and parameter sampling (#4160 ) * Introduced the Constant Parameter Sampler that will be useful later as samplers and floats can be used interchangeably * Refactored the settings.py to refect the new format of the config.yaml * First working version * Added the unit tests * Update to Upgrade for Updates * fixing the tests * Upgraded the config files * Fixes * Additional error catching * addressing some comments * Making the code nicer with cattr * Added and registered an unstructure hook for PrameterRandomization * Updating C# Walljump * Adding comments * Add test for settings export (#4164) * Add test for settings export * Update ml-agents/mlagents/trainers/tests/test_settings.py Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com> * Including environment parameters for the test for settings export * First documentation up...	4 年前
yanchaosun	66c4e6ff	new config	4 年前
yanchaosun	a212fef9	new bisim implementation	4 年前
yanchaosun	5471699d	crawler config	4 年前
HH	b877d953	remove unneeded config	4 年前
HH	0fdac847	Merge branch 'master' into hh/develop/crawler-ragdoll-updates	4 年前
yanchaosun	6daa2ed7	cloud config	4 年前
yanchaosun	9599a8ec	new config	4 年前
Andrew Cohen	5fa28f5f	merge YC changes	4 年前
Andrew Cohen	dad084ee	old crawler config	4 年前
Andrew Cohen	b46d3214	crawler configs	4 年前
Andrew Cohen	29af84da	action encoder configs	4 年前
yanchaosun	80bad241	init sac transfer, and added action encoder to bisim; configs for crawler	4 年前
Andrew Cohen	1e05e727	fix crawler yaml	4 年前
yanchaosun	f81feec4	config fix; basic sac	4 年前
HH	9e6edb6c	try new reward falloff	4 年前
Andrew Cohen	e6066ffd	separate value train and model schedule to const	4 年前
yanchaosun	a505cb16	new config	4 年前
HH	c3c83920	cleanup	4 年前
Andrew Cohen	240919b1	2 layer policy	4 年前
yanchaosun	9a19f6e5	disable bisim	4 年前
Andrew Cohen	35e9df24	value layers 3	4 年前
yanchaosun	c1bccaf5	diable bisim	4 年前
Andrew Cohen	36fa1614	model linear lr	4 年前
yanchaosun	62284176	change id	4 年前
Andrew Cohen	2213a071	policy linear lr	4 年前
Andrew Cohen	d8c123a0	Merge branch 'master' into sensitivity	4 年前
Andrew Cohen	33a906ad	add forward layer	4 年前
yanchaosun	6657129c	config: not reuse encoder	4 年前
HH	e2217a9a	new curve	4 年前
Andrew Cohen	0c7db26a	target encoder	4 年前
Andrew Cohen	57f247d4	targ for both	4 年前
yanchaosun	0c468084	sac transfer implementation; disable action encoder	4 年前
Ruo-Ping Dong	262f38ea	add basketball example	4 年前
Andrew Cohen	5d8b5274	add load model false to config	4 年前
yanchaosun	0a1a30d3	sac update	4 年前
Andrew Cohen	5524d6f3	test reuse	4 年前
yanchaosun	7226256d	config: no alter	4 年前
Andrew Cohen	cb60aa53	no separate vf	4 年前
yanchaosun	a9c6105d	configs	4 年前
Andrew Cohen	288eb0ed	reuse encoder false	4 年前
yanchaosun	00bb821c	fix sac transfer problems	4 年前
Andrew Cohen	6979a952	3dball transfers	4 年前
yanchaosun	e2f0b3ca	fix transfer	4 年前
Andrew Cohen	83bc38fd	try reuse encoder	4 年前
HH	00cb4c89	add WalkerStaticVariableSpeedScene and PPO config	4 年前
yanchaosun	cc9a38ae	cloud config with shared encoder	4 年前
Andrew Cohen	89abe29d	op buffer	4 年前
yanchaosun	2b67d1a6	fix crawler config	4 年前
HH	7c63197e	start dynamic cleanup and more debug for NaNs	4 年前
yanchaosun	42c0c333	fig bug	4 年前
Andrew Cohen	9c012d6a	no op buffer no acen	4 年前
yanchaosun	d1f57dec	separate value net config	4 年前
Andrew Cohen	d94b81c0	sep value false	4 年前
yanchaosun	910707dd	PPO 3dball config	4 年前
Andrew Cohen	2dc3c84c	add forward layer	4 年前
yanchaosun	f55fd920	remove transfer from yaml	4 年前
Andrew Cohen	2dec257c	no encoder for single task	4 年前
yanchaosun	d706f28c	use off policy buffer to transfer	4 年前
HH	977287dd	add all scenes	4 年前
Andrew Cohen	0198e41a	0 fwl	4 年前
yanchaosun	f937aa96	3dball ppo: without var predict	4 年前
Andrew Cohen	3513d5a6	load policy/vf	4 年前
yanchaosun	36f36750	target critic for ppo	4 年前
Andrew Cohen	bfd6a029	load value	4 年前
yanchaosun	6df774ed	update: separate model train as an option	4 年前
Andrew Cohen	e1ea3dca	load pol	4 年前
yanchaosun	aa0e896f	linear value, no target	4 年前
Andrew Cohen	78943972	add l2 penalty 3dball	4 年前
yanchaosun	c48b6429	numpy fix, config 3dball	4 年前
yanchaosun	8c03c82a	use target	4 年前
HH	b88434f8	increase to 30M	4 年前
Andrew Cohen	efa9e471	inc 3dball steps	4 年前
yanchaosun	44312bdb	linear policy and linear forward	4 年前
yanchaosun	57d3ba64	change path	4 年前
yanchaosun	42c9ba43	reuse encoder and linear	4 年前
Andrew Cohen	a65bd13e	no fw lay	4 年前
yanchaosun	e8fcc4bb	ppo new implementation	4 年前
Andrew Cohen	bec3f28c	no load policy	4 年前
Andrew Cohen	462b34fc	fw lay	4 年前
yanchaosun	66bbdae9	sac crawler configs	4 年前
Andrew Cohen	ad9e2eea	fewer features	4 年前
yanchaosun	120d1c3a	cloud config: non-linear policy	4 年前
yanchaosun	f78940c1	less features	4 年前
Andrew Cohen	2cd0de04	action enc	4 年前
yanchaosun	2d1ffac5	ppo ball	4 年前
HH	8eaddb61	Merge branch 'master' into hh/develop/loco-walker-variable-speed	4 年前
Andrew Cohen	12f3786c	Revert "action enc" This reverts commit 9acb5f846a77a47d14694cb1271e2a370f395b6a.	4 年前
yanchaosun	3ce88589	1 layer everything	4 年前
Andrew Cohen	014fc5fc	new crawler	4 年前
yanchaosun	86da272d	load pv	4 年前
yanchaosun	6220f7c7	linear model	4 年前
yanchaosun	f1346bdf	multiple seeds	4 年前
HH	c038362c	use all bp for avg vel	4 年前
yanchaosun	de4870be	new configs	4 年前
GitHub	b51347ac	New Variable Speed Walker Environments (#4301 ) * init * Add reward manager and hurryUpReward * fix hurry reward/ add awful first training * Turn off head height and hurry rew * changed max speed to 15. added small hh rew * add NaN check for reward manager. start vel penalty * add bpVel pen * add new BPVelPen nn file * remove outdated nn file * add randomize speed bool * try rewad product * change coeff to 1 * try avg vel of all bp for reward * move outside loop * try linear inverselerp for vel * add avg rew matchspeed15 nn file. looks much better * save scene * no hand penalty, random walk speed * fix inverse lerp * try new reward falloff * cleanup * added new nn file. don't allow hand contact * update obsv * remove hh rew. add trained no-hh model * add new nn file * new curve * add new models. try no reset * add hh rew * clamp hh * zero rewards if ground contact * switch to approved with movi...	4 年前
Andrew Cohen	69bf67f3	fix config	4 年前
HH	1bbd76fe	update prefabs	4 年前
Andrew Cohen	40f7b9e6	no val sep	4 年前
yanchaosun	4f64d0f5	new config	4 年前
Ervin Teng	d65a9326	Merge branch 'master' into develop-add-fire-mm3	4 年前
Ruo-Ping Dong	d57aa9ab	Merge branch 'develop-add-fire-mm3' into develop-add-fire-checkpoint	4 年前
Ervin Teng	7032fe82	Reduce max steps for striker vs. goalie	4 年前
HH	ef62939e	updating prefabs	4 年前
Andrew Cohen	eace3365	linear 3dball	4 年前
yanchaosun	0646e095	crawler configs	4 年前
yanchaosun	6b8a6e45	fix path	4 年前
GitHub	bd6bcd2f	Merge master and add Saver class for save/load checkpoints	4 年前
yanchaosun	990d25e3	fix path again	4 年前
Andrew Cohen	12eda929	try reload all	4 年前
yanchaosun	09e1f0c4	another fix	4 年前
Ervin Teng	42e25b25	Merge branch 'develop-add-fire' into develop-add-fire-memoryclass	4 年前
Andrew Cohen	70f05c39	reduce max step	4 年前
yanchaosun	fec40537	ppo crawler	4 年前
Andrew Cohen	b822283f	merge add fire	4 年前
Christopher Goy	5a233353	Merge remote-tracking branch 'origin/master' into release_6-to-master	4 年前
Andrew Cohen	764122ac	crawler update	4 年前
yanchaosun	15b2e80e	action encoder	4 年前
yanchaosun	b5e02978	sac crawler config	4 年前
yanchaosun	685c4d67	ppo crawler transfer	4 年前
yanchaosun	5ed6bd3e	sac crawler	4 年前
Andrew Cohen	5f7a7e44	revert tennis config	4 年前
yanchaosun	d6f8995a	larger feature size	4 年前
yanchaosun	ee48cca4	linear v	4 年前
GitHub	abfadb3d	Reduce max steps for striker vs. goalie (#4377 )	4 年前
HH	7e7743d1	update static prefabs	4 年前
yanchaosun	49d6b70c	crawler: max episode length=1000; new config: 1 forward layer	4 年前
Ervin Teng	6455654b	Shorten max steps for strikergoalie	4 年前
yanchaosun	4b081de4	smaller feature size	4 年前
HH	e3b1c5cf	add nn files. update to 15M steps	4 年前
yanchaosun	96b5478f	smaller	4 年前
GitHub	a79aa854	[ci] Shorten max steps for strikergoalie (#4394 )	4 年前
yanchaosun	0463bfe9	smaller state feature, large action feature	4 年前
yanchaosun	2e927257	separate policy net	4 年前
vincentpierre	ba7eb360	Merge branch 'master' into develop-torch-save-rp	4 年前
yanchaosun	86830ac9	3dball mass=5 transfer test	4 年前
yanchaosun	dd0ac8a3	mass=2	4 年前
HH	5bedaef6	add configs	4 年前
HH	f0a12c70	update configs/prefabs	4 年前
yanchaosun	46817bed	fix bug	4 年前
HH	a9d9ea4c	Merge branch 'master' into hh/develop/loco-crawler-variable-speed	4 年前
Scott Jordan	3d98516d	incorporated task parameter channel branch added the ability to set task parameters from python	4 年前
yanchaosun	b0f6f307	transfer from mass 2 to mass 1	4 年前
yanchaosun	bcdc0a11	f512	4 年前
Anupam Bhatnagar	f4f1a8d9	merge master into trainer-plugin branch	4 年前
Scott Jordan	56745026	Initial commit of running active learning code Active learning code is running on walker variable speed. Needs to be tested to see if it is working.	4 年前
yanchaosun	4a23dbb3	fix mass 3dball	4 年前
Scott Jordan	78f8a9a2	Updated task manager active learning is no optional and defaults to uniform sampling of tasks. Renamed ActiveLearningTaskManager to just TaskManager	4 年前
yanchaosun	db30f918	push block	4 年前
yanchaosun	4be4f1d1	new reacher env	4 年前
yanchaosun	e9a3ea57	reacher self-transfer	4 年前
yanchaosun	f1802c3a	push block transfer setting	4 年前
vincentpierre	0dd5effa	DO NOT MERGE	4 年前
vincentpierre	7cfb763d	[DO NOT MERGE]	4 年前
yanchaosun	5cab2114	push block without action encoder	4 年前
vincentpierre	9b8924a6	-	4 年前
Scott Jordan	e33168d6	Added comments and new yaml files for variable speed walker	4 年前
yanchaosun	4133fb35	no action	4 年前
vincentpierre	e2e62cb9	-	4 年前
yanchaosun	191a1133	block forward 2 layers	4 年前
yanchaosun	1ee62100	reacher	4 年前
yanchaosun	5c3306ef	large buffer size	4 年前
yanchaosun	4d5f5888	encoder layer 1	4 年前
GitHub	a117c932	Grid Sensor (#4399 ) Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
vincentpierre	3b8a8971	no threading	4 年前
yanchaosun	e39986ed	block larger feature size; reacher fix and new reward	4 年前
yanchaosun	7dac3284	push block more steps	4 年前
yanchaosun	51491a3e	new dynamics change: scale 1 to 2	4 年前
GitHub	582859b6	New Crawler Variable Speed Scenes (#4382 ) * init * updating prefabs * spawn a target * add brains * update static prefabs * enable enhanced determinism * reset manifest * add nn files. update to 15M steps * update prefabs * increase max speed to 15 * add new local model for 15 speed * update prefabs * add configs * update configs/prefabs * cleanup * added final nn models * add new demos and do more cleanup. * add meta files * add RigidbodySensor * update prefab. about to retrain * remove body pen * add fixed crawler & retrained nn file, new demos * train 10M steps * Update Crawler Docs * more prefab cleanup * add meta files * Update Project/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com> * remove unused prefab * update comment * add summary tags * cleanup and add more comments * remove unused prefab * Update P...	4 年前
yanchaosun	a1859fb8	reacher multi seeds	4 年前
yanchaosun	854e10e1	3dball hard scale	4 年前
GitHub	cc10cd82	Worm Ragdoll & Env Updates (#4413 ) * add worm updates * add rewman * cp * normalize rewards * only cookie * try 20M. Add3.5Mnn file * reduce strength to 3000spring * facing reward troubleshooting * Update WormAgent.cs * troubleshoot nan * try product of rewards * train 5M steps * try end episode on target touch * fix joint obsv * use 7M steps * added nn file for observation joint fix. looks great * don't end episode * remove old code * refactor to patterns used in walker & crawler * add auto-setup code * reformat * use head vel * remove unneeded observ. update prefabs * update static scenes * keeps rolling. added debug. try 5 m/s * gate the facing reward based on angle tolerance * added 10ms_angle30rew_nn files * use fromto rot * use 7M steps * add new trained files. cleanup code and prefabs * use avgvel. add code comments * remove unused method * add more comments * Update Learning-E...	4 年前
yanchaosun	b5a1b9b4	hard task name change	4 年前
yanchaosun	27dffa4d	new reacher reward	4 年前
yanchaosun	16e63cb8	config fix	4 年前
yanchaosun	883361ee	reacher new reward: action penalty and constant not-reaching-goal penalty	4 年前
yanchaosun	85549b2b	reacher: stack observation. with the original reward function	4 年前
Ervin Teng	333af451	Turn off threading	4 年前
yanchaosun	92c3facf	distance based penalty	4 年前
yanchaosun	f15a4f2d	2 layers	4 年前
yanchaosun	716336bf	larger feature size	4 年前
yanchaosun	63cec035	fix config	4 年前
Ervin Teng	3a7cd3ad	Merge experiments	4 年前
yanchaosun	693c0ca4	feature size 32	4 年前
yanchaosun	1a9aaaf6	model weights and large transfer learning weight	4 年前
yanchaosun	1ebe7054	new config	4 年前
yanchaosun	8f67cd40	smaller learning rate	4 年前
Andrew Cohen	3997b14b	Merge branch 'master' into develop-hybrid-actions	4 年前
vincentpierre	49e08218	-	4 年前
Ervin Teng	d4beb937	Make 3dball longer	4 年前
vincentpierre	c10da7ef	-	4 年前
GitHub	60b76790	Random Network Distillation for Torch (#4473 ) * initial commit * works with Pyramids * added unit tests and a separate config file * Adding first batch of documentation * adding in the docs that rnd is only for PyTorch * adding newline at the end of the config files * adding some docs * Code comments * no normalization of the reward * Fixing the tests * [skip ci] * [skip ci] Make sure RND will only work for Torch by editing the config file * [skip ci] Additional information in the Documentation * Remove the _has_updated_once flag	4 年前
Ervin Teng	b98e7c28	Use constant LR	4 年前
HH	0d42b277	train combo. added nn files.	4 年前
HH	d02c90f6	added more variants	4 年前
HH	1912e47a	Dynamic Sensor Benchmarks In	4 年前
GitHub	9e1a28c2	Add vector flag of agent's frozen state to VisualFoodCollector (#4511 ) VisualFoodCollector is now an example environment of using a mix of visual and vector observation and is able to train with default config file. Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
GitHub	b33e310f	Add Visual3DBall scene (#4513 ) * Add Visual3DBall scene which use visual observations with stacking	4 年前
Andrew Cohen	e5f14400	Merge branch 'master' into develop-hybrid-actions-singleton	4 年前
Andrew Cohen	2f870407	bullet hell game	4 年前
Ervin Teng	56196761	hyperparameteers and tweaks	4 年前
GitHub	90a9d214	Match3 example (#4515 )	4 年前
Ervin Teng	89489ae0	Invert divide by 3 in log prob	4 年前
GitHub	88d3ec3e	Merge master into hybrid actions staging branch (#4704 )	4 年前
Ervin Teng	7bec1df2	Better hyperparams	4 年前
HH	281e0be1	added sensors & controls UI	4 年前
Chris Elion	8cf87ed6	match3 settings	4 年前
Ervin Teng	e1378efc	Merge commit '6d729a0a2b2ba1fc946720cdb7871c9be3e38d45' into develop-fix-nan	4 年前
Ervin Teng	4c49f181	Change num envs	4 年前
vincentpierre	e14e1c4d	Improvements and new tests	4 年前
Andrew Cohen	d62f6b0a	modify bullet/attn	4 年前
GitHub	edc2ae2f	[bug-fix] Disable threading for self-play envs (#4679 )	4 年前
Ervin Teng	ce7d34a3	Revert "Invert divide by 3 in log prob" This reverts commit a708af66e740f19df5082b4b4e152a566c703385.	4 年前
GitHub	63704803	[bug-fix] Disable threading for self-play envs (#4679 ) (#4681 )	4 年前
Andrew Cohen	ef8f70e8	Add WalljumpPushblock env	4 年前
Ervin Teng	5130c9b3	Add walljump collab YAML	4 年前
GitHub	cc6b4564	Multi Directional Walker and Initial Hypernetwork (#4740 )	4 年前
Ervin Teng	d816513e	Add config and group ids to HallwayCollab	4 年前
Andrew Cohen	8a95b0bb	rays and disc	4 年前
Andrew Cohen	5b2e704f	updated heuristic	4 年前
Andrew Cohen	5bbe796b	update soccer raycasts	4 年前
Andrew Cohen	34420044	fix trainer c and soccer config	4 年前
Andrew Cohen	ca5a5194	soccer comms on the cloud	4 年前
Andrew Cohen	12828bdc	remove tau from diff for	4 年前
HH	16acb693	update max steps and add config	4 年前
HH	fce83c8a	try curiosity	4 年前
HH	9d17392a	about to merge in master	4 年前
HH	dd1fbd8a	update config to train 5M steps	4 年前
Andrew Cohen	c183040a	update soccer scene	4 年前
vincentpierre	f7a4a31f	[Experiment] Bullet hell	4 年前
Andrew Cohen	f57875e0	layer norm	4 年前
Andrew Cohen	6fae089e	bullet config	4 年前
Andrew Cohen	a6294e38	run bullet on cloud	4 年前
HH	5c5539af	add zomb scene	4 年前
HH	fd7d9c4a	add trained models	4 年前
HH	a738d235	add new env scene	4 年前
Andrew Cohen	32d77b5e	Merge branch 'develop-hybrid-action-staging' into develop-hybrid-actions-singleton	4 年前
Andrew Cohen	e2506856	sequence env	4 年前
Andrew Cohen	bedf9886	update sequencer env	4 年前
Andrew Cohen	9effa1b5	update sorter yaml	4 年前
Ruo-Ping Dong	a7d04be6	Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp	4 年前
HH	a29ce02c	train 4 env	4 年前
Ruo-Ping Dong	224d2087	add team reward	4 年前
Ervin Teng	384bfaac	Add configuration yaml for pushblockcollab	4 年前
Andrew Cohen	fecddfed	refactored sequence env	4 年前
Andrew Cohen	3a4aa513	COMAA runs	4 年前
Andrew Cohen	5741f8f6	no target net	4 年前
Arthur Juliani	1cf97635	Additional conditional experiments	4 年前
Andrew Cohen	a4c336c2	value estimator	4 年前
Arthur Juliani	d2526ce2	Modify CrawlerDynamic	4 年前
Andrew Cohen	2792cc87	update coma config	4 年前
Andrew Cohen	6c6d54b0	cubewars config	4 年前
Andrew Cohen	bd341f7f	no target, increase lambda	4 年前
Andrew Cohen	00e3c5c5	fix config	4 年前
GitHub	8cf3b93b	Merge pull request #4741 from Unity-Technologies/walljump-pushblock Add WalljumpPushblock env	4 年前
Arthur Juliani	759fd2b5	PushJump modifications	4 年前
Andrew Cohen	e997a5fc	cloud config	4 年前
Arthur Juliani	b84b4880	Add GoalNav environment	4 年前
Andrew Cohen	fce842aa	adding zombie to coma2 brnch	4 年前
Andrew Cohen	b0bf7817	clipping values and updated zombie	4 年前
Andrew Cohen	da4f4ae8	update configs	4 年前
vincentpierre	8dd003e6	-	4 年前
Andrew Cohen	869a2811	update zombie config	4 年前
Andrew Cohen	2047ab1f	cubewars config	4 年前
vincentpierre	48bd37ee	-	4 年前
Ervin Teng	e9e80149	Change names of behaviors	4 年前
Andrew Cohen	e1061302	config	4 年前
Ervin Teng	f4f559da	Remove a bunch of stuff from envs	4 年前
Ervin Teng	844b5955	Remove a bunch of extra files	4 年前
Ervin Teng	985c80d7	Remove remaining files	4 年前
GitHub	ed28d1ba	[MLA-1768] retrain Match3 scene (#4943 ) * improved settings and move to default_settings * update models	4 年前
vincentpierre	fdf21dbd	addressing some of the comments	4 年前
GitHub	307d7cd2	Merge pull request #4912 from Unity-Technologies/develop-var-len-obs-feature-refactor-model-loader-checks Develop var len obs feature refactor model loader checks	4 年前
vincentpierre	695c02fd	[skip ci] Attempting new config	4 年前
vincentpierre	272097ed	new curriculum	4 年前
vincentpierre	9f51d91a	New curriculum, new model	4 年前
Christopher Goy	9cadfa7a	Merge master -> release_13_branch-to-master	4 年前
GitHub	332e9b8b	Merge pull request #4909 from Unity-Technologies/develop-var-len-obs-feature Develop var len obs feature	4 年前
Ruo-Ping Dong	b5da488d	Merge branch 'master' into develop-base-teammanager	4 年前
Andrew Cohen	dc8e8494	Merge branch 'master' into develop-critic-optimizer	4 年前
Chris Elion	e4f51ca7	Merge remote-tracking branch 'origin/master' into MLA-1734-demo-provider	4 年前
Ervin Teng	93a59971	Merge branch 'develop-critic-optimizer' into develop-critic-op-lstm	4 年前
Ervin Teng	d4438878	Merge branch 'develop-base-teammanager' into develop-agentprocessor-teammanager	4 年前
vincentpierre	3499a645	-	4 年前
GitHub	4d5545c8	Set ignore done=False in GAIL (#4971 )	4 年前
Ervin Teng	f409c40c	Merge branch 'master' into develop-agentprocessor-teammanager	4 年前
Ervin Teng	e46a86ad	Merge branch 'master' into develop-superpush-int	4 年前
HH	15d512f9	Merge branch 'master' into hh/develop/dodgeball	4 年前
Ervin Teng	08db7c2f	Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer-mm	4 年前
vincentpierre	8f729b75	Fixing the number of layers in the config of PyramidsRND	4 年前
GitHub	5ce1083b	Merge pull request #5006 from Unity-Technologies/fix-num-layers-rnd-pyramids Fixing the number of layers in the config of PyramidsRND	4 年前
Christopher Goy	747e2228	Merge branch 'master' into release_13_branch-to-master	4 年前
GitHub	ccca1309	Merge pull request #5007 from Unity-Technologies/release_13_branch-to-master Release 13 branch to master	4 年前
Ervin Teng	4b159789	Add PushBlockCollab config and fix some stuff	4 年前
Chris Elion	f5bf6e08	simple TicTacToe example	4 年前
HH	4c947151	Merge branch 'main' into hh/develop/dodgeball	4 年前
Ervin Teng	61781a1a	Merge branch 'main' into develop-agentprocessor-teammanager	4 年前
Andrew Cohen	9060da06	Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer	4 年前
HH	1f8aa5c3	add simple training scene	4 年前
Arthur Juliani	06c147f8	Merge remote-tracking branch 'origin/main' into goal-conditioning-new # Conflicts: # Project/Assets/ML-Agents/Examples/Crawler/Prefabs/CrawlerBase.prefab # Project/Assets/ML-Agents/Examples/GridWorld/Prefabs/Area.prefab # Project/Assets/ML-Agents/Examples/GridWorld/Scenes/GridWorld.unity # Project/ProjectSettings/TagManager.asset # com.unity.ml-agents/Runtime/Sensors/CameraSensor.cs # com.unity.ml-agents/Runtime/Sensors/VectorSensor.cs # ml-agents/mlagents/trainers/torch/networks.py # ml-agents/mlagents/trainers/torch/utils.py	4 年前
Ervin Teng	c8137dcd	Merge branch 'main' into develop-superpush-int	4 年前
GitHub	85f8b40b	Removing some scenes (#4997 ) * Removing some scenes, All the Static and all the non variable speed environments. Also removed Bouncer, PushBlock, WallJump and reacher. Removed a bunch of visual environements as well. Removed 3DBallHard and FoodCollector (kept Visual and Grid FoodCollector) * readding 3DBallHard * readding pushblock and walljump * Removing tennis * removing mentions of removed environments * removing unused images * Renaming Crawler demos * renaming some demo files * removing and modifying some config files * new examples image? * removing Bouncer from build list * replacing the Bouncer environment with Match3 for llapi tests * Typo in yamato test	4 年前
GitHub	21623b50	renaming of behavior name for imitation crawler (#5039 )	4 年前
GitHub	f16ce486	Update v2-staging from main (March 15) (#5123 )	4 年前
Ervin Teng	d9cbae07	Dodgeball config update	4 年前
Christopher Goy	921ba4f0	Update v2-staging from main (March 15) (#5123 )	4 年前
GitHub	ba2af269	[coma2] Make group extrinsic reward part of extrinsic (#5033 ) * Make group extrinsic part of extrinsic * Fix test and init * Fix tests and bug * Add baseline loss to TensorBoard	4 年前
Ervin Teng	f45afff3	Different YAML settings	4 年前
Ervin Teng	d5aee550	Add num_envs for cloud run	4 年前
Christopher Goy	ebe45056	Merge branch 'main' into release_14_branch-to-main	4 年前
Ervin Teng	8902c058	Merge branch 'main' into develop-coma2-trainer	4 年前
Chris Elion	970f1d40	Merge remote-tracking branch 'origin/v2-staging' into MLA-1634-ObservationSpec	4 年前
Ervin Teng	1f026c70	Merge branch 'main' into develop-superpush-branch-cleanup	4 年前
Ervin Teng	8263eb52	Backup more changes	4 年前
Ervin Teng	ce872033	Revert "Merge branch 'main' into develop-superpush-branch-cleanup" This reverts commit 5bea802525381f931a5e0f8b8778fe27a12f03af, reversing changes made to cee3524e85161e13689d95f66bc6bff994d2cdfd.	4 年前
Ervin Teng	8ef2c390	Merge branch 'develop-superpush-branch-cleanup' into develop-pushcollabonly	4 年前
GitHub	d015ef17	[environment] Push Block Collaborative (#5090 ) * Add pushblock collab * Make SimpleMultiAgentGroup public * Remove GoalDetectTrigger * Remove GDT meta file * Remove some comments * Add training configuration * Rename behavior * Add to docs * Change the reward structure in docs * Add back GoalDetectTrigger Co-authored-by: HH <brandonh@unity3d.com>	4 年前
Andrew Cohen	9e77d7e1	Merge branch 'main' into develop-soccer-groupman	4 年前
GitHub	62aa3d47	Move PushBlockCollab config to poca directory (#5097 )	4 年前
Ervin Teng	09e7e805	[cherry-pick] Move PushBlockCollab config to poca directory (#5097 )	4 年前
Andrew Cohen	d95d8d92	soccer fours, agent prefabs	4 年前
Andrew Cohen	9176247c	Merge branch 'main' into develop-soccer-groupman-mod	4 年前
GitHub	6895ba50	Integrate Group Manager to soccer/retrain with POCA (#5115 )	4 年前
Andrew Cohen	25be5ff7	increase beta	4 年前
HH	02ac5091	add actuated sensors & rbsensor	4 年前
GitHub	d2ee2e6f	[cherry-pick] Integrate Group Manager to soccer/retrain with POCA (#5115 ) (#5121 ) * Integrate Group Manager to soccer/retrain with POCA (#5115) * Add Soccer env to changelog Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>	4 年前
GitHub	31e72e67	Add DungeonEscape POCA Environment (#5128 ) * Add DungeonEscape assets from working branch * Add Dungeon Escape docs * Create dungeon_escape.png	4 年前
GitHub	fe1d3e26	Fix GridFoodCollector yaml (#5134 )	4 年前
GitHub	f7ab0cb0	[cherry-pick][docs] Add Dungeon Escape Environment (#5133 ) * Add DungeonEscape POCA Environment (#5128) * Add DungeonEscape assets from working branch * Add Dungeon Escape docs * Create dungeon_escape.png * Add to docs Co-authored-by: Hunter-Unity <hunter@unity3d.com>	4 年前
GitHub	6eef8929	Fix GridFoodCollector yaml (#5134 ) (#5136 ) Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>	4 年前
GitHub	43147c1a	Remove env settings from Sorter (#5146 )	4 年前
GitHub	65cd8dab	Remove env settings from Sorter (#5145 )	4 年前
Christopher Goy	eeeb7ba3	upate scene layout.	4 年前
Ervin Teng	75d9cf59	Fix path to PushBlock demo (#5198 ) (cherry picked from commit 875feb01509d8191fc3cc60d6a08c931546fb6dc)	4 年前
Ervin Teng	c108da4a	[bug-fix] Fix POCA LSTM, pad sequences in the back (#5206 ) * Pad buffer at the end * Fix padding in optimizer value estimate * Fix additional bugs and POCA * Fix groupmate obs, add tests * Update changelog * Improve tests * Address comments * Fix poca test * Fix buffer test * Increase entropy for Hallway * Add EOF newline * Fix Behavior Name * Address comments (cherry picked from commit 2ce6810846ba9268e4fb5fb082fa54e90414c980)	4 年前
vincentpierre	42a3732c	Code improvements	4 年前
Andrew Cohen	18be47e8	Merge branch 'main' into develop-soccer-groupman-mod	4 年前
GitHub	dc807346	Reduce pb collab steps to 15M (#5196 )	4 年前
GitHub	119503db	Fix path to PushBlock demo (#5198 )	4 年前
vincentpierre	7fa8b242	Code improvements	4 年前
GitHub	2980ade0	Goal conditioning grid world : Example of goal conditioning (#5193 ) * Aded the Goal conditioned GridWorld to replace regular gridworld * adding missing files * Code improvements * Documentation change on gridworld * resolving conflicts * new model * Addressing comments * comments and renames * Update docs/Learning-Environment-Examples.md Co-authored-by: Ervin T. <ervin@unity3d.com> * adding reference to gridworld in docs about goal signal Co-authored-by: Chris Elion <chris.elion@unity3d.com> Co-authored-by: Ervin T. <ervin@unity3d.com>	4 年前
GitHub	c5589b59	[bug-fix] Fix POCA LSTM, pad sequences in the back (#5206 ) * Pad buffer at the end * Fix padding in optimizer value estimate * Fix additional bugs and POCA * Fix groupmate obs, add tests * Update changelog * Improve tests * Address comments * Fix poca test * Fix buffer test * Increase entropy for Hallway * Add EOF newline * Fix Behavior Name * Address comments	4 年前
GitHub	45e75e01	[config] Disable `threading` by default (#5221 ) * Remove threading as default * New description * Remove threaded option from YAML configs * Remove from Match3	4 年前
vincentpierre	4e14879d	Updating the barracuda 1.4.0 (#5291 ) Initial commit second commit. The no-extrinsic was trained without the log reward (reward = prob) while the new one is (reward = log_prob - log_prior) A few results, it looks like Walker-diverse-r05-bigger.onnx is doing something Modified pushblock using next state and action. Did not help Fixing bug that had 9 diversity settings instead of 8 removing results	4 年前
vincentpierre	bab3ecb7	First version of MEDE, crawler does not seem to work properly, I suspect the actions make it distinguishable to the discriminator but not to the human eye	4 年前
Andrew Cohen	d813bfd5	continuous, crawler integrated, new cube	4 年前
vincentpierre	8da21669	Adding some changes	4 年前
vincentpierre	47fa1682	-	4 年前
vincentpierre	7c74c967	_	4 年前
vincentpierre	8450b154	-	4 年前
vincentpierre	5985959d	Got 2 modes on Wlker I think	4 年前
Scott	130512b4	fixed episode length modification issue.	3 年前
Scott	97990611	Added decision frequency and evaluation metric	3 年前
GitHub	f0159e00	Better hyperparameters for Hallway-SAC (#5339 )	4 年前
GitHub	5e1df27b	[ci] Shorten SAC runs (#5354 )	4 年前
Miguel Alonso Jr	97b7d5c6	Merge branch 'main' into develop-api-documentation-update Syncing with main.	4 年前

1 2 3 4 5 ...

766 次代码提交 (7e7743d1-03a2-4a84-a127-380dea067341)