ml-agents

作者	SHA1	备注	提交日期
Ervin Teng	fe4472cb	Add decoders, distributions, encoders, layers, networks, and utils	4 年前
Ervin Teng	89890bf2	Update with newest changes	4 年前
GitHub	e3bc3352	[pytorch] Add decoders, distributions, encoders, layers, networks, and utils (#4349 )	4 年前
GitHub	1955af9e	[feature] Add experimental PyTorch support (#4335 ) * Begin porting work * Add ResNet and distributions * Dynamically construct actor and critic * Initial optimizer port * Refactoring policy and optimizer * Resolving a few bugs * Share more code between tf and torch policies * Slightly closer to running model * Training runs, but doesn’t actually work * Fix a couple additional bugs * Add conditional sigma for distribution * Fix normalization * Support discrete actions as well * Continuous and discrete now train * Mulkti-discrete now working * Visual observations now train as well * GRU in-progress and dynamic cnns * Fix for memories * Remove unused arg * Combine actor and critic classes. Initial export. * Support tf and pytorch alongside one another * Prepare model for onnx export * Use LSTM and fix a few merge errors * Fix bug in probs calculation * Optimize np -> tensor operations * Time action sample funct...	4 年前
vincentpierre	9f51ab14	Saving the reward providers	4 年前
vincentpierre	25454a48	adding tests	4 年前
vincentpierre	108fac9a	Replace torch.detach().cpu().numpy() with a utils method	4 年前
GitHub	328353bc	Torch : Saving/Loading of the reward providers (#4405 ) * Saving the reward providers * adding tests * Moved the tests around * Update ml-agents/mlagents/trainers/tests/torch/saver/test_saver_reward_providers.py * Update ml-agents/mlagents/trainers/tests/torch/saver/test_saver_reward_providers.py * Update ml-agents/mlagents/trainers/tests/torch/saver/test_saver_reward_providers.py Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com> * Update ml-agents/mlagents/trainers/tests/torch/saver/test_saver_reward_providers.py Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com> Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com>	4 年前
vincentpierre	31750e97	Using item() in place of to_numpy()	4 年前
Andrew Cohen	6587c911	hybrid bheavior spec	4 年前
Ruo-Ping Dong	88eff042	Merge branch 'master' into develop-saver-name	4 年前
Anupam Bhatnagar	f4f1a8d9	merge master into trainer-plugin branch	4 年前
GitHub	12e15e29	Fix on GAIL Torch when using actions (#4407 )	4 年前
GitHub	498934f9	Replace torch.detach().cpu().numpy() with a utils method (#4406 ) * Replace torch.detach().cpu().numpy() with a utils method * Using item() in place of to_numpy() * more use of item() and additional tests	4 年前
Andrew Cohen	5b1620e9	moved encoders to processors	4 年前
Ruo-Ping Dong	27fb4270	brain_name to behavior_name	4 年前
Ervin Teng	1dca75d8	Move linear encoding to NetworkBody	4 年前
GitHub	bfda9576	Replace brain_name with behavior_name (#4419 ) brain_name -> behavior_name some prob -> log_prob in comments rename files optimizer -> optimizer_tf for tensorflow	4 年前
GitHub	9364048e	Merge branch 'develop-pytorch-encoding' into develop-restructure-torch-networks	4 年前
Ruo-Ping Dong	fd1dc3a6	Merge branch 'master' into develop-torch-omp	4 年前
Ruo-Ping Dong	f5dee9d1	jit for continuous control	4 年前
Ruo-Ping Dong	ef3be79e	sac	4 年前
GitHub	7b4d0865	[Bug fix] Fix bug in GAIL gradient penalty (#4425 )	4 年前
GitHub	4e93cb6e	[torch] Restructure PyTorch encoders (#4421 ) * Move linear encoding to NetworkBody * moved encoders to processors (#4420) * fix bad merge * Get it running * Replace mentions of visual_encoders * Remove output_size property * Fix tests * Fix some references * Revert test_simple_rl * Fix networks test * Make curiosity test more accomodating * Rename total_input_size * [Bug fix] Fix bug in GAIL gradient penalty (#4425) (#4426) Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com> * Up number of steps * Rename to visual_processors and vector_processors Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com> Co-authored-by: Andrew Cohen <andrew.cohen@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
GitHub	beb5eb30	[bug-fix] Fixes for Torch SAC and tests (#4408 ) * Fixes for Torch SAC and tests * FIx recurrent sac test * Properly update normalization for SAC-continuous * Fix issue with log ent coef reporting in SAC Torch	4 年前
GitHub	6f534366	Add torch_utils class, auto-detect CUDA availability (#4403 ) * Add torch_utils * Use torch from torch_utils * Add torch to banned modules in CI * Better import error handling * Fix flake8 errors * Address comments * Move networks to GPU if enabled * Switch to torch_utils * More flake8 problems * Move reward providers to GPU/CPU * Remove anothere set default tensor * Fix banned import in test	4 年前
GitHub	676f5f7c	[refactor] Refactor GAIL to use new encoder structure (#4433 ) Co-authored-by: Ervin Teng <ervin@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
Ervin Teng	60eacc0d	Merge branch 'master' into develop-adjust-cpu-settings	4 年前
GitHub	6986fb10	use LinearEncoder in curiosity and clean up (#4444 )	4 年前
Ervin Teng	fdc887a1	Some experimental stuff	4 年前
GitHub	bf6506fc	[feature] Add small CNN for grids 5x5 and up (#4434 )	4 年前
Andrew Cohen	3997b14b	Merge branch 'master' into develop-hybrid-actions	4 年前
GitHub	069f10b9	[Bug fix] Export all branches for discrete control torch (#4491 ) * Export all branches for discrete control torch * [skip ci] Changelog edits * Update ml-agents/mlagents/trainers/torch/networks.py Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com> * Update ml-agents/mlagents/trainers/torch/networks.py * Fix formatting Co-authored-by: Ruo-Ping (Rachel) Dong <ruoping.dong@unity3d.com>	4 年前
Ervin Teng	14a7e29b	Add AMRL layer	4 年前
Andrew Cohen	8294bc59	ignore commit	4 年前
GitHub	fc557903	Develop fix visual torchh export (#4494 ) * Fixing exporting of ONNX for visual when using threading * docstring was wrong	4 年前
Ervin Teng	3e771cbb	Permute visual obs outside of network	4 年前
Ervin Teng	9f96a495	Use built-in cumulative max	4 年前
Andrew Cohen	b0b2e22e	prepare to merge action_out	4 年前
Ervin Teng	77c810fb	Fix SAC and make utility method	4 年前
Ervin Teng	43c41d66	Fix BC and Reward Signals	4 年前
Ervin Teng	7754ad7b	Don't run value during inference	4 年前
Ervin Teng	3f7d815c	detach masks	4 年前
GitHub	10f3e1c7	Cherry picked #4491 (#4493 ) [Bug fix] Export all branches for discrete control torch	4 年前
GitHub	37645aa2	Develop fix visual torchh export (#4494 ) (#4497 ) * Fixing exporting of ONNX for visual when using threading * docstring was wrong	4 年前
Andrew Cohen	85602279	add action_out to dist	4 年前
Ervin Teng	b6095151	Execute critic with LSTM	4 年前
vincentpierre	181bdec0	-	4 年前
GitHub	4e4ad7b0	Don't run value during policy evaluate, optimized soft update function (#4501 ) * Don't run value during inference * Execute critic with LSTM * Address comments * Unformat * Optimized soft update * Move soft update to model utils * Add test for soft update	4 年前
Andrew Cohen	f0a2c6f2	add action_out abstract method and docstring	4 年前
Ervin Teng	f9ff3efe	Merge branch 'develop-policyonly' into develop-sac-targetq	4 年前
Andrew Cohen	7c0aa77b	Merge branch 'develop-actions-out' into develop-hybrid-actions	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
Andrew Cohen	b6b453a0	rename to exported model output	4 年前
Andrew Cohen	9cbf6c3f	Merge branch 'develop-actions-out' into develop-hybrid-actions	4 年前
Andrew Cohen	72cd0d39	separate tensors for disc/cont	4 年前
Andrew Cohen	643c8e58	ppo extended	4 年前
Ervin Teng	ba29b6b4	Change dimensions of recurrent in to BxN for ONNX	4 年前
GitHub	400e14cb	[Bug-fix] RND would not be saved correctly. Added tests (#4514 )	4 年前
Andrew Cohen	db37db34	fixing errors	4 年前
Andrew Cohen	44c9879e	action models	4 年前
HH	a3bf96fd	Merge branch 'master' into hh/develop/gridsensor-tests	4 年前
Andrew Cohen	c494bfcc	trains successfully	4 年前
Ervin Teng	e8431a6d	Proper dimensions for entropy, sum before bonus in PPO	4 年前
Andrew Cohen	190d8e4d	action model as a singleton	4 年前
Ervin Teng	8dec4771	Add hybrid actions to SAC	4 年前
Andrew Cohen	d6544353	using lists for distributions	4 年前
Andrew Cohen	e686a785	removed abstract class	4 年前
Ervin Teng	81342148	Revert "Add hybrid actions to SAC" This reverts commit a759b36a51df4f8f1fd296f9f148269f0f026e42.	4 年前
Andrew Cohen	74553853	use ModuleList	4 年前
Andrew Cohen	aa5cf8ab	rename ActionModel	4 年前
Andrew Cohen	4b9a7db6	remove old behaviorspec	4 年前
Andrew Cohen	5a3f5b4a	remove comments	4 年前
Andrew Cohen	e5f14400	Merge branch 'master' into develop-hybrid-actions-singleton	4 年前
GitHub	e4db5dc5	ActionSpec and ActionBuffer (#4578 )	4 年前
Andrew Cohen	eaecb59e	torch utils to and from buffer	4 年前
Andrew Cohen	6e23bafd	ActionFlattener Refactor	4 年前
Andrew Cohen	8013e544	ignoring Instance of 'AbstractContextManager' has no 'enter_context' member (no-member)	4 年前
GitHub	e0ef30a5	[bug-fix] Change entropy computation and loss reporting in Torch to match TF (#4538 ) * Proper dimensions for entropy, sum before bonus in PPO * Make entropy reporting same as TF * Always use separate critic * Revert to shared * Remove unneeded extra line * Change entropy shape in test * Change another entropy shape * Add entropy summing to evaluate_actions * Add notes about torch.abs(policy_loss)	4 年前
GitHub	cb8e4d25	Add ActionSpec (#4586 ) Co-authored-by: Ervin T <ervin@unity3d.com>	4 年前
Andrew Cohen	b40e7793	fix mlagents-envs tests	4 年前
GitHub	a4ba90ec	[bug-fix] Fix ONNX export/Barracuda import for continuous actions (#4608 ) * Use torch.ones rather than expand * use tf.cat instead of tf.expand for Barracuda * fix error msg handling * handle loading exception Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
Andrew Cohen	9689cf2c	remove _action_ from function names	4 年前
GitHub	64e998a2	[bug-fix] Use float64 when converting np.ndarray to torch.tensor, cap Torch version to 1.7.x (#4610 ) * Use float64 in GAIL tests * Use float32 when converting np arrays by default * Enforce torch 1.7.x or below * Add comment about Windows install * Adjust tests	4 年前
vincentpierre	96452986	Initial commit for multi head attention	4 年前
Andrew Cohen	dc89318d	remove ActionType	4 年前
vincentpierre	a3a9a56b	Merge branch 'exp-multi-head-attention' into exp-bullet-hell	4 年前
Ruo-Ping Dong	9e08be87	Merge branch 'master' into release_9_branch_merge	4 年前
Ervin Teng	99ec16e6	Hard Swish	4 年前
Andrew Cohen	6cf54bf2	remove self.action_spec from policy/bc	4 年前
vincentpierre	d3d4eb90	Trainer with attention	4 年前
Ervin Teng	5d3ad161	Leaky ReLU	4 年前
Andrew Cohen	97dfa142	fix action_spec refs	4 年前
vincentpierre	7ef3c9a1	Trainer with attention	4 年前
Ervin Teng	f00ff21d	Add clipping to Torch	4 年前
GitHub	b853e5ba	Action buffer (#4612 ) Co-authored-by: Ervin T <ervin@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
vincentpierre	b09dfd0a	Still not working	4 年前
Ervin Teng	7e6cc222	Take mean of continuous entropy	4 年前
Ervin Teng	e80d418b	Use lower scaling value	4 年前
Ervin Teng	89489ae0	Invert divide by 3 in log prob	4 年前
GitHub	3c96a3a2	Action Model (#4580 ) Co-authored-by: Ervin T <ervin@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
Andrew Cohen	0e28dd8f	add static method to create continuous/discrete	4 年前
vincentpierre	c264b4da	additional changes	4 年前
Ervin Teng	7502a383	Proper dimensions	4 年前
Ervin Teng	c3cec801	Use linear gain for KaimingHe	4 年前
Ervin Teng	1f305f24	Test commit	4 年前
GitHub	88d3ec3e	Merge master into hybrid actions staging branch (#4704 )	4 年前
Ervin Teng	48a11a0e	Undo test commit	4 年前
Ervin Teng	66f3d2ad	Merge branch 'develop-contentropy' into develop-torch-clip	4 年前
Andrew Cohen	ae920478	resolve conflicts	4 年前
vincentpierre	9b3d4ade	Fixing some issues	4 年前
GitHub	87a7ccf8	use int64 steps, check for NaN actions (#4607 ) * use int64 steps * check for NaN actions Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com>	4 年前
Ervin Teng	db6ebff6	Remove clip	4 年前
GitHub	23800f33	Merge branch 'master' into develop-action-spec	4 年前
GitHub	85a7c0f7	[bug-fix] Add clipping to PyTorch policy, fix initialization (#4649 )	4 年前
Ervin Teng	08c8862e	Add epsilon to log	4 年前
Ervin Teng	0548057d	Use real clipping (as in TF)	4 年前
Ervin Teng	0cdb2040	Use tanh squash	4 年前
Andrew Cohen	719d94e9	fix entropy_sum after merge	4 年前
vincentpierre	6fcbba53	Refactoring the code to make it more flexible. Still a hack	4 年前
Ervin Teng	eb4f3065	Add another epsilon	4 年前
GitHub	733bffbf	use int64 steps, check for NaN actions (#4607 ) (#4654 ) * use int64 steps * check for NaN actions Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com> Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
Ervin Teng	23b42dcd	Merge branch 'develop-torchcrawlerdebug' into develop-torch-clip	4 年前
vincentpierre	58f38662	Bigger network, needed to solve	4 年前
GitHub	efdb1042	Add global lock for torch.onnx.export() (#4659 )	4 年前
Ervin Teng	adc039a5	Use linear gain for KaimingHe	4 年前
vincentpierre	0b6c2ed3	Fixing some bugs	4 年前
GitHub	8175d558	[bug-fix] Fix BC module + action clipping (#4667 )	4 年前
GitHub	2a8c6800	[bug-fix] Add clipping to PyTorch policy, fix initialization (#4649 ) (#4662 )	4 年前
Ervin Teng	3b3b53e2	Improve comment	4 年前
Andrew Cohen	c74adb81	fix specs in torch util	4 年前
Andrew Cohen	84cc2b84	concat x self before attention	4 年前
vincentpierre	e14e1c4d	Improvements and new tests	4 年前
GitHub	de27d7a6	[bug-fix] Fix issue where NaNs are outputted by the policy when training Match3 (#4664 ) * match3 settings * Add epsilon to log * Add another epsilon * Revert match3 configs * NaN-free masking method * Add comment for paper * Add comment for paper Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
Ruo-Ping Dong	953cb6bb	Merge branch 'master' into develop-windows-delay	4 年前
GitHub	8df04e83	Add global lock for torch.onnx.export() (#4665 ) * Cherry-pick fix from #4659	4 年前
Andrew Cohen	d62f6b0a	modify bullet/attn	4 年前
GitHub	1cac78e2	[Bug-fix] Remove extra directory created at checkpoint (#4675 ) * [Bug-fix] Remove extra directory created at checkpoint * removing os import	4 年前
Ervin Teng	bc746839	Normalize GAIL observations	4 年前
Ruo-Ping Dong	ee5313e4	Merge branch 'master' into develop-windows-delay	4 年前
Ervin Teng	78f88c15	Add clip to export and make optional in policy	4 年前
vincentpierre	f283cb60	different architecture	4 年前
Ervin Teng	362f2ec0	Use correct dimensions of gradient	4 年前
GitHub	f0ed3a38	Cherry-pick BC fixes to Release 10 (#4668 )	4 年前
GitHub	b6c903c8	Cherry-pick NaN fix for Match 3 (#4664 ) * match3 settings * Add epsilon to log * Add another epsilon * Revert match3 configs * NaN-free masking method * Add comment for paper * Add comment for paper Co-authored-by: Chris Elion <chris.elion@unity3d.com> Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
Ervin Teng	3eba7423	Increase initialization	4 年前
GitHub	fd31da37	[Bug-fix] Remove extra directory created at checkpoint (#4675 ) (#4678 ) * [Bug-fix] Remove extra directory created at checkpoint * removing os import	4 年前
Ervin Teng	4f8f21e4	Bigger scale	4 年前
Andrew Cohen	3f771e61	add ActionBuffers and utils	4 年前
Ervin Teng	7a0ebfbd	Pretty broken	4 年前
Ervin Teng	95bdbba3	Less broken PPO	4 年前
Ervin Teng	6c77ac7a	Update SAC, fix PPO batching	4 年前
GitHub	278911a5	Fix staging tests (#4708 )	4 年前
Ervin Teng	1db21cbb	Fix SAC interrupted condition and typing	4 年前
GitHub	94c59e31	C# changes for hybrid action spaces (#4587 ) * Add hybrid action capability flag (#4576) * Change BrainParametersProto to support ActionSpec (#4579) * Assign new BrainParametersProto fields based on capabilities (#4581) * ActionBuffer with hybrid actions for RemotePolicy (#4592) * Barracuda inference for hybrid actions (#4611) * Refactor BarracudaModel loader checks (#4629) * Export separate nodes for continuous/discrete actions (#4655) * Separate continuous/discrete actions in AgentActionProto (#4698) * Force different nodes for new and deprecated action output (#4705)	4 年前
Ervin Teng	4158629e	Properly feed in None rather than empty arrays	4 年前
Andrew Cohen	bd917c9c	action buffer passes continuous	4 年前
vincentpierre	90da7426	Fix masking for torch	4 年前
Ervin Teng	5a5bd515	Fix multiple obs	4 年前
Andrew Cohen	b36fcf16	discrete runs/cont passes	4 年前
vincentpierre	e85d8e35	Added a comment and included the change of #4715 for simplicity	4 年前
Ervin Teng	8d29114d	Update curiosity reward provider	4 年前
Andrew Cohen	ad951493	debugging discrete	4 年前
Ervin Teng	79a3051e	Update GAIL and BC	4 年前
Andrew Cohen	fcf6471e	2d discrete passes	4 年前
GitHub	2c744129	Merge pull request #4714 from Unity-Technologies/develop-fix-mask Fix masking for torch	4 年前
Ervin Teng	fdaa8c3d	Merge branch 'develop-unified-obs' into develop-centralizedcritic	4 年前
Andrew Cohen	056630d7	sac continuous and discrete train	4 年前
GitHub	990f801a	Develop hybrid action staging (#4702 ) Co-authored-by: Ervin T <ervin@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com> Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com> Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
vincentpierre	735fcd52	[WIP] Refactor trainers to use list of obs rather than vec and vis obs	4 年前
Ervin Teng	6846af21	Multi-input network	4 年前
Andrew Cohen	85e4db33	bc tests pass	4 年前
vincentpierre	93ca1409	fixing the tests	4 年前
vincentpierre	7a5cc9ec	Merge master into develop-rm-tf	4 年前
Ervin Teng	cb4b7ed3	Some minor tweaks but still broken	4 年前
Andrew Cohen	24fd9b3c	torch reward providers all pass	4 年前
vincentpierre	12619155	added some docstrings	4 年前
Andrew Cohen	dee6b805	fixed bug in discrete	4 年前
vincentpierre	c1587bce	Solving merge conflicts	4 年前
Ervin Teng	2b8ab09d	Use Vince's ONNX export code	4 年前
Ervin Teng	558bfb70	Cleanup	4 年前
Andrew Cohen	b5d1c071	Merge branch 'master' into develop-action-buffer	4 年前
Arthur Juliani	0d2f8887	Merge remote-tracking branch 'origin/master' into goal-conditioning # Conflicts: # ml-agents-envs/mlagents_envs/base_env.py # ml-agents-envs/mlagents_envs/rpc_utils.py # ml-agents/mlagents/trainers/tests/mock_brain.py # ml-agents/mlagents/trainers/tests/simple_test_envs.py	4 年前
Andrew Cohen	73b778cc	rename extract to from_dict	4 年前
GitHub	cc6b4564	Multi Directional Walker and Initial Hypernetwork (#4740 )	4 年前
Ervin Teng	25dfd883	Merge branch 'master' into develop-centralizedcritic	4 年前
GitHub	ad5f878c	[refactor] Remove critic pass during inference (#4743 )	4 年前
GitHub	11687f8d	[cherry-pick] Cherry-pick #4743 into Release 11 (#4756 )	4 年前
GitHub	22658a40	use sensor types to differentiate obs (#4749 )	4 年前
vincentpierre	14378aa5	Merging master	4 年前
vincentpierre	0c81006d	addressing comments	4 年前
Ervin Teng	ecac7ca1	Set num teammates to 2	4 年前
Arthur Juliani	95441b75	Use separate hypernetwork module	4 年前
Arthur Juliani	03ee5833	black formatting	4 年前
Andrew Cohen	eef14922	discrete/contionuous unity envs train	4 年前
Arthur Juliani	79898e06	Use hypernetwork in both places	4 年前
Arthur Juliani	f36b10d8	Fix typo	4 年前
Andrew Cohen	a545859e	fix torch test policy	4 年前
Andrew Cohen	43387daa	remove unused import	4 年前
vincentpierre	8cb050ef	WIP Made initial changes to enale dimension properties and added attention module	4 年前
GitHub	6f4f6044	Fix model inference issue with Barracuda v1.2.1 (#4766 ) (#4768 ) Co-authored-by: Ervin T. <ervin@unity3d.com>	4 年前
Ervin Teng	170c269e	Remove prints	4 年前
Andrew Cohen	e168bb4f	add docstrings to AgentAction and ActionLogProbs	4 年前
GitHub	9fbf56e2	Fix model inference issue with Barracuda v1.2.1 (#4766 ) Co-authored-by: Ervin T. <ervin@unity3d.com>	4 年前
Andrew Cohen	498b1ee6	Merge branch 'develop-action-buffer' into develop-hybrid-actions-singleton	4 年前
GitHub	a73f7d73	Turn down gain on GAIL discriminator output (#4762 )	4 年前
Andrew Cohen	06f1f254	1:1 and continuous/discrete train	4 年前
Andrew Cohen	7750bccd	all hybrid simple rl tests pass	4 年前
Ervin Teng	2462db69	Add comment to ghost trainer	4 年前
GitHub	559609a2	Update ml-agents/mlagents/trainers/torch/utils.py Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
Andrew Cohen	6174c428	move action model to explicit distributions	4 年前
GitHub	b6bb01b9	Turn down gain on GAIL discriminator output (#4762 ) (#4772 )	4 年前
vincentpierre	c3699de8	merging master and addressing comments	4 年前
Ervin Teng	f207a1a6	Revert "Add comment to ghost trainer" This reverts commit 292b6ce672a7a23ebfdd76bf07b11c50a825dcf4.	4 年前
vincentpierre	e0cf88e6	Made a nicer comment	4 年前
Andrew Cohen	f2c9d184	fix set_actions_for_agent	4 年前
GitHub	29d94c7c	Merge pull request #4734 from Unity-Technologies/develop-obs-as-list Refactor trainers to use list of obs rather than vec and vis obs	4 年前
Ervin Teng	e4e0e2bd	Scale size of CC network	4 年前
Andrew Cohen	1d234d1d	bc works	4 年前
vincentpierre	719c969c	addressing comments. ObservationSpec is no longer a list	4 年前
Ervin Teng	a3885120	Scale value network based on num agents	4 年前
Andrew Cohen	8d7e449f	torch curiosity tests pass	4 年前
vincentpierre	4bba4e8e	Renaming ObservationSpec to SensorSpec	4 年前
Andrew Cohen	7973b46c	remove print bc	4 年前
Andrew Cohen	c0d01baf	Merge branch 'master' into merge-release11-master	4 年前
Andrew Cohen	95566e44	Merge branch 'develop-action-buffer' into develop-hybrid-actions-singleton	4 年前
vincentpierre	c5a057d2	renaming obs_spec variables	4 年前
HH	0cc4eed4	Merge branch 'develop-centralizedcritic' into hh/develop-pushblockcollab	4 年前
Andrew Cohen	e81e68de	comms agent and fixed hallway	4 年前
vincentpierre	44ed3258	Merging master	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
Andrew Cohen	8543b917	add kickpower bonus	4 年前
Andrew Cohen	708ac9bf	use hard=true gbsm	4 年前
vincentpierre	449712b0	renaming sensor_spec to sensor_specS	4 年前
Andrew Cohen	35769b53	Merge branch 'develop-action-buffer' into develop-hybrid-actions-singleton	4 年前
Andrew Cohen	c843e3d4	hallway collab exps on cloud	4 年前
Andrew Cohen	272affe0	preliminary aciton model tests	4 年前
Andrew Cohen	a20287f7	continuous comms	4 年前
Andrew Cohen	17496265	move AgentAction, ActionLogProbs, and ActionFlattener to separate files	4 年前
vincentpierre	f7a4a31f	[Experiment] Bullet hell	4 年前
Chris Elion	76ebc20c	Merge remote-tracking branch 'origin/master' into r12-to-master	4 年前
Andrew Cohen	2dc2ffe3	add action util files	4 年前
Andrew Cohen	f57875e0	layer norm	4 年前
GitHub	458fee17	Merge pull request #4763 from Unity-Technologies/develop-att WIP Made initial changes to enable dimension properties and added attention module	4 年前
vincentpierre	36cc4665	Removing some vis and vec fields from policy.py	4 年前
Andrew Cohen	bc77c990	layer norm and weight decay with fixed architecture	4 年前
GitHub	e344fe79	Make memory contiguous (#4804 )	4 年前
vincentpierre	ab0dd150	formatting	4 年前
Ervin Teng	330fc1d0	Merge branch 'master' into develop-centralizedcritic-mm	4 年前
vincentpierre	519c5f47	merging master	4 年前
Andrew Cohen	fad37dc5	add default args to LinearEncoder	4 年前
Ervin Teng	ad439fb6	Additional changes	4 年前
vincentpierre	a482a47c	fixing tests	4 年前
Andrew Cohen	21365c04	formatting	4 年前
Ervin Teng	d02a1033	Some more fixes	4 年前
Ruo-Ping Dong	8ed14762	Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp	4 年前
Andrew Cohen	7ba10239	remove action spec attribute from policy	4 年前
Andrew Cohen	96c01a63	custom layer norm	4 年前
Ervin Teng	efa67290	Self-attention Centralized Critic	4 年前
Andrew Cohen	662fd6b1	added docstrings to action flattener	4 年前
GitHub	a272bff0	Merge pull request #4803 from Unity-Technologies/develop-remove-vec-vis-fields Remove some vis and vec fields from Policy	4 年前
GitHub	d7c3022d	Export separate nodes for continuous/discrete actions (#4655 )	4 年前
Andrew Cohen	d0c8b5f1	added docstrings to action model	4 年前
Andrew Cohen	90e0e8b2	concat self	4 年前
HH	5c5539af	add zomb scene	4 年前
GitHub	cc948a41	Policy output actiontuple (#4651 )	4 年前
Andrew Cohen	89ed777e	increase bullets to 40	4 年前
Andrew Cohen	886883b3	Merge branch 'develop-hybrid-action-staging' into develop-hybrid-actions-singleton	4 年前
Andrew Cohen	60816204	revert changes to 20 bullets	4 年前
Andrew Cohen	231328ea	remove warning prints	4 年前
GitHub	9689449f	Refactor of attention (#4840 ) Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
Andrew Cohen	010803ea	separate entity encoder and RSA	4 年前
Arthur Juliani	0b4b0992	Rename more files	4 年前
Andrew Cohen	3ca65063	clean up args in mha	4 年前
Arthur Juliani	7c37c759	Fix some mis-renamings	4 年前
Andrew Cohen	701c1a3f	fix test torch distributions	4 年前
GitHub	b7e6efa3	Allow setting maximum number of elements in self-attention to None (#4841 ) * separate entity encoder and RSA * clean up args in mha * more cleanups * fixed tests * entity embeddings have no max option * Add exceptions for variable export * Fix test * Add docstrings Co-authored-by: Andrew Cohen <andrew.cohen@unity3d.com>	4 年前
vincentpierre	56972f56	WIP integrate attention to networkbody	4 年前
Andrew Cohen	540b930b	add defaults to linear encoder, initialize ent encoders	4 年前
Andrew Cohen	9ae8a720	more cleanups	4 年前
Ervin Teng	aba633b2	Merge branch 'develop-attention-refactor' into develop-centralizedcritic-mm	4 年前
vincentpierre	d27459bd	Fix error in embedding	4 年前
Andrew Cohen	631ac7f4	fixed tests	4 年前
Ervin Teng	30a09c6f	Merge branch 'develop-attention-refactor' into develop-centralizedcritic-mm	4 年前
GitHub	eb78a477	Add default init/gain to LinearEncoder (#4846 )	4 年前
Ervin Teng	135914fd	entity embeddings work with no max Integrate into CC	4 年前
GitHub	0ac990e0	add LayerNorm (#4847 )	4 年前
vincentpierre	af58753b	adding encoding to self and var len input	4 年前
Ervin Teng	e05e897c	One layer for entity embed	4 年前
vincentpierre	8c1a33a4	Fixing .contiguous missing in resnet	4 年前
vincentpierre	edbac259	Fixing merge conflicts	4 年前
Ervin Teng	9a3598eb	Use 4 heads	4 年前
Ruo-Ping Dong	a7d04be6	Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp	4 年前
GitHub	d30e9f28	Merge pull request #4851 from Unity-Technologies/fix-contiguous-resnet Fixing .contiguous missing in resnet	4 年前
vincentpierre	5039b65a	Merge branch 'master' into develop-att-network-integration	4 年前
Arthur Juliani	0a876b9c	Fix typos	4 年前
Ervin Teng	2085e17c	Merge branch 'master' into develop-centralizedcritic-mm	4 年前
Ruo-Ping Dong	d3348074	fix policy action_spec typo	4 年前
vincentpierre	e7024786	Removing hacky layer norm	4 年前
Arthur Juliani	e3de0406	Plurals	4 年前
Ervin Teng	dfe07e1d	Merge branch 'develop-lin-enc-def' into develop-centralizedcritic-mm	4 年前
Ruo-Ping Dong	180d3e20	Merge branch 'develop-centralizedcritic-mm' into develop-cc-teammanager	4 年前
HH	0024a286	merge ervin's new stuff	4 年前
GitHub	12e1fc28	[feature] Hybrid SAC (#4574 )	4 年前
Andrew Cohen	b0c02ee0	Merge branch 'develop-hybrid-actions-csharp' into develop-actionmodel-csharp	4 年前
Ervin Teng	9c3da1b6	New buffer layout, TeamObsUtil, pad dead agents	4 年前
GitHub	67ad9651	Merge pull request #4825 from Unity-Technologies/sensor-types [WIP] Observation Types	4 年前
vincentpierre	8660b1c2	merging master	4 年前
Ervin Teng	eab7e42a	Use NaNs to get masks for attention	4 年前
Ervin Teng	3daa17a9	Merge branch 'develop-centralizedcritic-mm' into develop-zombieteammanager	4 年前
Arthur Juliani	da0c8b9d	Add hypernetwork	4 年前
Ervin Teng	bf7195f1	Refactor multi input network slightly	4 年前
Ervin Teng	1c557bd3	Don't concat self	4 年前
vincentpierre	38fc2536	addresing some comments	4 年前
Ervin Teng	6b8b3db3	Try subtract marginalized value	4 年前
Ervin Teng	92fc78a5	Use new trajectory	4 年前
Ervin Teng	b2c498de	Use NaNs to get masks for attention	4 年前
GitHub	e9ff7705	Fix torch tensor non-contiguous issue (#4855 ) * add contiguous * preserve tensor device type	4 年前
Andrew Cohen	ad807327	refactor entityembedding/network body	4 年前
GitHub	01e0ee00	refactor entityembedding/network body (#4857 )	4 年前
Ervin Teng	5d7345a6	Add Q function with attention	4 年前
Andrew Cohen	6e6f3246	clean up	4 年前
Ervin Teng	092ea232	Some more progress - still broken	4 年前
Andrew Cohen	4e37974c	moved embedding layer norm into network body	4 年前
GitHub	89b6c949	use singular entity embedding (#4873 )	4 年前
Ervin Teng	457b2630	I think it's running	4 年前
Andrew Cohen	5caaef52	move entity max computation to network body	4 年前
Ervin Teng	65b866b0	Actions added but untested	4 年前
Andrew Cohen	86d4c5c5	move embedding norm into RSA block	4 年前
Ervin Teng	3e481f7d	Fix issue with team_actions	4 年前
brccabral	457fb612	Merge branch 'master' of https://github.com/Unity-Technologies/ml-agents	4 年前
Ervin Teng	0919a32d	Add next action and next team obs	4 年前
Andrew Cohen	44088167	separate forward into q_net and baseline	4 年前
Andrew Cohen	07e92563	Merge branch 'develop-centralizedcritic-counterfact' into develop-coma2	4 年前
Andrew Cohen	6e1826f8	might be right	4 年前
vincentpierre	52b011d6	_	4 年前
vincentpierre	03c905b2	Fix equation for entropy	4 年前
Andrew Cohen	1511588d	forcing this to work	4 年前
vincentpierre	5f9ea5ea	_	4 年前
vincentpierre	396bc43c	Merging master	4 年前
GitHub	d4455936	Merge pull request #4869 from Unity-Technologies/fix-normal-entropy Fix equation for entropy	4 年前
vincentpierre	a4b78d53	_	4 年前
vincentpierre	b7c7d773	Adding some tests	4 年前
vincentpierre	6f3ea7b8	_	4 年前
vincentpierre	92005ea6	Better placeholder for encoded_self than None	4 年前
Andrew Cohen	feb38012	add lambda return and target network	4 年前
Arthur Juliani	e8d54b6f	Use hypernetwork if there is a goal	4 年前
vincentpierre	099a51ef	removing extra line	4 年前
vincentpierre	65c2fa7f	Making EntityEmbedding encode self and entities separately	4 年前
Arthur Juliani	512482c8	Check that goal is a goal	4 年前
GitHub	bd4bc66b	Merge branch 'master' into fix-numti-env-delayed-spawn	4 年前
vincentpierre	f101393c	Better bounds for log probabilities	4 年前
vincentpierre	77eecc6b	Merge branch 'master' into develop-att-network-integration	4 年前
Arthur Juliani	1cf97635	Additional conditional experiments	4 年前
vincentpierre	7e47f94b	addressing comments	4 年前
Andrew Cohen	a4c336c2	value estimator	4 年前
GitHub	d7f549f9	Run pytest on GPU (#4865 ) * make tests device-friendly * mark all tests in test_simple_rl	4 年前
Arthur Juliani	d2526ce2	Modify CrawlerDynamic	4 年前
GitHub	3c1e98ca	Update ml-agents/mlagents/trainers/torch/distributions.py	4 年前
vincentpierre	c27a95f0	Make a self encoder before EntityEmbedding	4 年前
Arthur Juliani	ff70c5c4	Merge branch 'master' into goal-conditioning-new	4 年前
vincentpierre	2bf6737f	addressing comments	4 年前
Arthur Juliani	b8e81b00	Make lists modulelists	4 年前
vincentpierre	fd007f53	Attempting to use EntityEmbedding directly as processor	4 年前
vincentpierre	efa5a164	addressing comments and adding the changes to rpc_utils	4 年前
Arthur Juliani	759fd2b5	PushJump modifications	4 年前
vincentpierre	19a8244b	[skip ci] Removing no-longer-useful comment We concatenate the encodes instead of adding them up	4 年前
Arthur Juliani	21aaa5fe	Add goal to hyper input	4 年前
Arthur Juliani	a180dbf7	Add visual version of task and simply encoders	4 年前
Andrew Cohen	7f491ae7	cloud run with coma2 of held out zombie test env	4 年前
vincentpierre	9fbc2e0e	_	4 年前
Arthur Juliani	7165e9cf	Make conditiontype a setting	4 年前
Andrew Cohen	9af22d30	use only value funcs	4 年前
vincentpierre	bf16bad6	_	4 年前
Andrew Cohen	511a9a7e	no baseline	4 年前
vincentpierre	6a61eb05	-	4 年前
vincentpierre	1acdc155	Changes to hypernet - - - experimenting -	4 年前
vincentpierre	82d80d72	better error message	4 年前
GitHub	2fb87e4f	Merge branch 'master' into reward-dist	4 年前
vincentpierre	04bdb40c	Reorder operations	4 年前
GitHub	212ebfb9	Merge pull request #4844 from Unity-Technologies/develop-att-network-integration Integrate attention to networkbody	4 年前
GitHub	ca8a4ae2	Merge pull request #4990 from Unity-Technologies/goal-conditioning-new-vince Tried to make improvements to the initialization of the hyperNetwork weights	4 年前
Andrew Cohen	687f411b	try again on cloud	4 年前
Chris Elion	9d70220e	Merge remote-tracking branch 'origin/master' into MLA-1734-demo-provider	4 年前
Arthur Juliani	1d106816	Support multiple goals in networkbody	4 年前
Arthur Juliani	7ba4ca17	Reformat line	4 年前
Arthur Juliani	2552cf18	Address comments	4 年前
GitHub	001990af	Merge pull request #5008 from Unity-Technologies/multi-goal-conditioning Support multiple goals in networkbody	4 年前
Andrew Cohen	f9ff3fef	shared baseline and v	4 年前
Ervin Teng	bca6c92c	Add clipping, use same network for value	4 年前
Arthur Juliani	4413203d	Sensor cleanup	4 年前
Ervin Teng	3283b6a1	Remove Q-net for perf	4 年前
GitHub	64fc7f43	Buffer key enums (#4907 )	4 年前
Ervin Teng	2be83146	Use same network	4 年前
Ervin Teng	6094613d	try reduce bias more	4 年前
vincentpierre	8baaaf4d	Changing model export to be compatible with Barracuda	4 年前
Andrew Cohen	c08fefbc	reduce initialization weights	4 年前
Ervin Teng	b6f88d6d	Merge branch 'develop-base-teammanager' into develop-agentprocessor-teammanager	4 年前
Andrew Cohen	eeabb974	Separate Actor/Critic, remove ActorCritics	4 年前
Andrew Cohen	6bd396ee	add critic to optimizer, ppo runs	4 年前
Ervin Teng	c7054d76	Use attention tests from master	4 年前
Ervin Teng	0bde7598	Back out trainer changes	4 年前
Ervin Teng	da6a55a0	Revert "Use attention tests from master" This reverts commit 78e052be8f36381bb6857817ff0f505716be83b9.	4 年前
Ervin Teng	7c826fb1	Working GRU	4 年前
Ervin Teng	514873bf	Use correct memories (t-1 instead of t) for training	4 年前
Ervin Teng	bac2fb68	Use attention from master	4 年前
Ervin Teng	e9025079	Properly use MemoryModule abstraction	4 年前
Andrew Cohen	c74dca9f	add SharedActorCritic	4 年前
Ervin Teng	f3a2a81f	Merge branch 'develop-fix-lstms' into develop-gru	4 年前
Ruo-Ping Dong	c87bce9e	Merge branch 'master' into develop-base-teammanager	4 年前
Ervin Teng	a9116382	Bug fixes	4 年前
Andrew Cohen	98d647de	MultiInputNetBody	4 年前
vincentpierre	bd6ab0f7	Silencing a Torch warning that raises when exporting the attention module to ONNX	4 年前
Christopher Goy	9cadfa7a	Merge master -> release_13_branch-to-master	4 年前
vincentpierre	e1b94b8b	Merge branch 'master' into develop-var-len-obs-feature	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
Ervin Teng	fd3f05b9	Enable GAIL to decay	4 年前
vincentpierre	811319c0	Use clipped gaussian distribution for entropy calculation	4 年前
Ervin Teng	7b41e5d6	Add GAIL learning rate to TB	4 年前
GitHub	4d5545c8	Set ignore done=False in GAIL (#4971 )	4 年前
Chris Elion	c3bc8991	cleanup, don't store mask	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
Ervin Teng	3d2171c4	Add team methods to AgentAction	4 年前
Ervin Teng	9bc88c41	Running COMA (not sure if learning)	4 年前
Ervin Teng	12cef7af	Add test for GroupObs	4 年前
Ervin Teng	1fc3640e	Change AgentAction back to 0 pad and add tests	4 年前
Ervin Teng	c6904f86	Group reward function	4 年前
Ervin Teng	ffdfd8ff	Address some comments	4 年前
GitHub	338af2ec	Move the Critic into the Optimizer (#4939 ) Co-authored-by: Ervin Teng <ervin@unity3d.com>	4 年前
Ervin Teng	13fca55f	Add more comments	4 年前
Ervin Teng	60f2b72e	Rename internal function	4 年前
Ervin Teng	be45d8c0	Move padding method to AgentBufferField	4 年前
HH	4c947151	Merge branch 'main' into hh/develop/dodgeball	4 年前
vincentpierre	22db0335	Modified the model_serialization to have correct inputs and outputs	4 年前
Ervin Teng	61781a1a	Merge branch 'main' into develop-agentprocessor-teammanager	4 年前
vincentpierre	5b5171f8	switching from CamelCase to snake_case	4 年前
Andrew Cohen	9060da06	Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer	4 年前
vincentpierre	3068ae1f	Adding a helper method for creating observation placeholder names and removed the _h and _c placeholders	4 年前
Ervin Teng	56d4c1f9	Fix to-flat and add tests	4 年前
Andrew Cohen	5d517c5e	clean ups	4 年前
Andrew Cohen	e2d46ca0	Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer	4 年前
Andrew Cohen	8562471e	add inital coma optimizer tests	4 年前
GitHub	c9c7e3d0	Faster NaN masking, fix masking for visual obs (#5015 ) * Fix get mask from visual obs, large obs perf imp. * Bug fix * Fix typo	4 年前
GitHub	c3c34267	Merge pull request #5018 from Unity-Technologies/develop-use-correct-names-for-recurrent-inputs-and-outputs Modified the model_serialization to have correct inputs and outputs	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
Arthur Juliani	f49dcf8e	Update network (partially)	4 年前
GitHub	d36a5242	Python Dataflow for Group Manager (#4926 ) * Make buffer type-agnostic * Edit types of Apped method * Change comment * Collaborative walljump * Make collab env harder * Add group ID * Add collab obs to trajectory * Fix bug; add critic_obs to buffer * Set group ids for some envs * Pretty broken * Less broken PPO * Update SAC, fix PPO batching * Fix SAC interrupted condition and typing * Fix SAC interrupted again * Remove erroneous file * Fix multiple obs * Update curiosity reward provider * Update GAIL and BC * Multi-input network * Some minor tweaks but still broken * Get next critic observations into value estimate * Temporarily disable exporting * Use Vince's ONNX export code * Cleanup * Add walljump collab YAML * Lower max height * Update prefab * Update prefab * Collaborative Hallway * Set num teammates to 2 * Add config and group ids to HallwayCollab * Fix bug with hallway collab * E...	4 年前
Ervin Teng	fd0dd35c	Merge branch 'main' into develop-coma2-trainer	4 年前
Arthur Juliani	ce1d3d88	Resolve conflicts in networkbody	4 年前
Ervin Teng	c8137dcd	Merge branch 'main' into develop-superpush-int	4 年前
Arthur Juliani	fc1ee931	Fix hypernetwork	4 年前
GitHub	0ddfbfee	V2 staging new model version (#5080 ) * Make modelCheck have flavors of error messages * ONNX exporter v3 * Using a better CheckType and a switch statement * Removing unused message * More tests * Use an enum for valid versions and use GetVersion on model directly * Maybe the model export version a static constant in Python * Use static constructor for FailedCheck * Use static constructor for FailedCheck * Modifying the docstrings * renaming LegacyDiscreteActionOutputApplier * removing testing code * better warning message * Nest the CheckTypeEnum into the FailedCheck class * Update com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs * Adding a line explaining that legacy tensor checks are for versions 1.X only * Modifying the changelog * Exporting all the branches size instead of omly the sum (#5092) * addressing comments * Update com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs Co-authored...	4 年前
Christopher Goy	d1acc658	V2 staging new model version (#5080 ) * Make modelCheck have flavors of error messages * ONNX exporter v3 * Using a better CheckType and a switch statement * Removing unused message * More tests * Use an enum for valid versions and use GetVersion on model directly * Maybe the model export version a static constant in Python * Use static constructor for FailedCheck * Use static constructor for FailedCheck * Modifying the docstrings * renaming LegacyDiscreteActionOutputApplier * removing testing code * better warning message * Nest the CheckTypeEnum into the FailedCheck class * Update com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs * Adding a line explaining that legacy tensor checks are for versions 1.X only * Modifying the changelog * Exporting all the branches size instead of omly the sum (#5092) * addressing comments * Update com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs Co-authored-by: Chris Elion <chris.elion@unity3d.co...	4 年前
Andrew Cohen	81524ee8	lstm almost runs	4 年前
GitHub	f16ce486	Update v2-staging from main (March 15) (#5123 )	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
Chris Elion	a362b3d9	Merge remote-tracking branch 'origin/v2-staging' into csharp-obs-spec	4 年前
GitHub	6ae8ea1e	[coma2] Add support for variable length obs in COMA2 (#5038 ) * Make group extrinsic part of extrinsic * Fix test and init * Fix tests and bug * Add baseline loss to TensorBoard * Add support for variable len obs in COMA2 * Remove weird merge artifact * Make agent action run * Fix __getitem__ replace with slice * Revert "Fix __getitem__ replace with slice" This reverts commit 87a2c9d9a9342a7d2be4e9f620d1294a5c3bf22c. * Revert "Make agent action run" This reverts commit 59531f3746c58d62cf52f58a88e27a3e428e8946.	4 年前
Christopher Goy	ebe45056	Merge branch 'main' into release_14_branch-to-main	4 年前
Andrew Cohen	0afe5f24	add slice function to agent action	4 年前
GitHub	d2635e58	Action slice (#5047 ) * add slice function to agent action * add type/docstring to slice * add test	4 年前
Andrew Cohen	cb13a8ca	add type/docstring to slice	4 年前
Andrew Cohen	f165bfb5	update comment	4 年前
Chris Elion	970f1d40	Merge remote-tracking branch 'origin/v2-staging' into MLA-1634-ObservationSpec	4 年前
GitHub	8f35bdd3	POCA trainer (#5005 ) Co-authored-by: Ervin Teng <ervin@unity3d.com> Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com> Co-authored-by: Chris Elion <chris.elion@unity3d.com> Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>	4 年前
Andrew Cohen	9e77d7e1	Merge branch 'main' into develop-soccer-groupman	4 年前
GitHub	e79d8a9d	[bug-fix] Move POCA critic to default device (#5124 ) * Move critic to default device * Make sure to clone onto default device * Add some debug stuff * Some more debug * Fix issue * Fix bool tensor too	4 年前
GitHub	e6143a83	[bug-fix] Move POCA critic to default device (#5124 ) (#5131 ) * Move critic to default device * Make sure to clone onto default device * Add some debug stuff * Some more debug * Fix issue * Fix bool tensor too	4 年前
GitHub	ef3d6e0d	Adding Hypernetwork modules and unit tests (#5141 )	4 年前
Ervin Teng	41dd16e8	Merge branch 'main' into release_15_mm	4 年前
Christopher Goy	90872d1d	V2 staging new model version (#5080 ) * Make modelCheck have flavors of error messages * ONNX exporter v3 * Using a better CheckType and a switch statement * Removing unused message * More tests * Use an enum for valid versions and use GetVersion on model directly * Maybe the model export version a static constant in Python * Use static constructor for FailedCheck * Use static constructor for FailedCheck * Modifying the docstrings * renaming LegacyDiscreteActionOutputApplier * removing testing code * better warning message * Nest the CheckTypeEnum into the FailedCheck class * Update com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs * Adding a line explaining that legacy tensor checks are for versions 1.X only * Modifying the changelog * Exporting all the branches size instead of omly the sum (#5092) * addressing comments * Update com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs Co-authored...	4 年前
vincentpierre	e83c350a	Fixing networks.py for the merge	4 年前
vincentpierre	9609c79c	Fixing networks.py for the merge	4 年前
GitHub	ea2b2f20	Merge pull request #5158 from Unity-Technologies/v2-staging-rebase-2-fix-networks Fixing networks.py for the merge	4 年前
GitHub	78851829	Merge pull request #5157 from Unity-Technologies/v2-staging-rebase-2 V2 Staging back to main	4 年前
Andrew Cohen	18be47e8	Merge branch 'main' into develop-soccer-groupman-mod	4 年前
GitHub	81705d6d	Goal conditioning integration (#5142 ) * Adding Hypernetwork modules and unit tests * Edits * Integration of the hypernetowrk to the trainer * Update ml-agents/mlagents/trainers/torch/networks.py Co-authored-by: Arthur Juliani <awjuliani@gmail.com> * Making the default hyper and added the conditioning type None * Reducing the number of hypernetwork layers * addressing comments Co-authored-by: Arthur Juliani <awjuliani@gmail.com>	4 年前
vincentpierre	d4716caa	Merge branch 'main' into goal-conditioning-sensors-3	4 年前
GitHub	c37cfac1	Adding the goal conditioning sensors with the new observation specs (#5159 ) * Fixing networks.py for the merge * fix compile error * Adding the goal conditioning sensors with the new observation specs * addressing feedback * I forgot to change the m_observationType * Renaming Goal to GoalSignal (#5190) * Renaming GOAL to GOAL_SIGNAL * VectorSensorComponent to use new API * Adding docstrings * verbose pytest on github action Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
vincentpierre	1b4fd8fb	Renaming GOAL to GOAL_SIGNAL	4 年前
GitHub	b9cab453	[perf] Optimizations for performance (#5192 ) * Lazy init the buffer when sampling * Update references rather than copy data * Don't create unneeded numpy arrays * Remove self[key] from loop	4 年前
GitHub	2e19759c	Turning some logger.info into logger.debug and remove some logging overhead when not using debug (#5211 ) * turning some logger.info into logger.debug and remove some logging overhead when not using debug * Addressing comments * Adding to changelog	4 年前
GitHub	dffc37bf	Update to barracuda 1.3.3 and changes to the model inputs and outputs for LSTM (#5236 ) * Initial commit * making it work with hallway. Added a new model version * addressing feedback * Adding a comment * formatting * modifying the changelog * Adding descriptions on the model version descriptions * Update com.unity.ml-agents/Runtime/Inference/GeneratorImpl.cs Co-authored-by: Chris Elion <chris.elion@unity3d.com> * addressing comments Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
vincentpierre	51adab1c	Fix the attention module embedding size	4 年前
GitHub	353b1566	Fix the attention module embedding size (#5272 ) * Fix the attention module embedding size * editing the changelog	4 年前
GitHub	1678be1c	POCA Attention will use h_size for embedding size and not 128 (#5281 )	4 年前
GitHub	5e25015f	POCA Attention will use h_size for embedding size and not 128 (#5281 ) (#5287 )	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	bf8acbb0	-	4 年前
Miguel Alonso Jr	4846cf0f	Merge branch 'main' into develop-api-documentation-update Updating with main.	4 年前
GitHub	806f04bd	Readding the validation of the minimal cnn input size (#5345 ) (#5346 )	4 年前
GitHub	15440c24	Readding the validation of the minimal cnn input size (#5345 )	4 年前
GitHub	bb07eb45	Adding a fully connected visual encoder for super small visual input + tests (#5351 ) * initial commit for a fully connected visual encoder * adding a test * addressing comments * Fixing error with minimal size of fully connected network * adding documentation and changelog	4 年前
GitHub	ce1808f2	[bug-fix] Make resnet barracuda-compatible (#5358 ) (#5364 ) Co-authored-by: Ervin T <ervin@unity3d.com>	4 年前
Miguel Alonso Jr	97b7d5c6	Merge branch 'main' into develop-api-documentation-update Syncing with main.	4 年前
GitHub	20c0c728	[bug-fix] Make resnet barracuda-compatible (#5358 )	4 年前
vincentpierre	983982ee	Removing misleading learning rate	4 年前

1 2 3 4 5 ...

507 次代码提交 (3ed6bb54-c9bf-45b2-a134-0208d2377bdc)