ml-agents

作者	SHA1	备注	提交日期
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
Ruo-Ping Dong	07e82899	update torch saver test	4 年前
GitHub	38e9387b	Fix NNCheckpointManager for Torch Fix NNCheckpointManager for Torch	4 年前
Ruo-Ping Dong	a74c904a	Merge branch 'master' into develop-saver-name	4 年前
GitHub	df685184	Make --torch use torch even without config (#4400 ) * Make --torch use torch even without config * Update ml-agents/mlagents/trainers/trainer_util.py Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com> * Update ml-agents/mlagents/trainers/trainer_util.py Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com> * Update ml-agents/mlagents/trainers/trainer_util.py Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com> * renaming use_torch to force_torch Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>	4 年前
GitHub	70197342	Add torch saver test Add torch saver test	4 年前
Ruo-Ping Dong	f2a8c421	add torch saver test	4 年前
Ruo-Ping Dong	09c22679	fix NNCheckpointManager for Torch	4 年前
Ruo-Ping Dong	c47ffc20	Rename saver	4 年前
GitHub	a79aa854	[ci] Shorten max steps for strikergoalie (#4394 )	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
GitHub	ea3944fc	DemonstrationRecorder: Add numStepsToRecord feature. (#4381 ) * add numSteps property and update recorder script * add changes based on PR suggestions * make zero default. update logic * updated comments & tooltip	4 年前
GitHub	a796b0f1	Merge pull request #4387 from Unity-Technologies/master-pin-xdist Pin xdist version.	4 年前
Christopher Goy	c448eb65	Pin xdist version on verfided branch.	4 年前
GitHub	b337e62b	add build-in module dependencies (#4384 ) * add build-in module dependencies * changelog	4 年前
GitHub	abfadb3d	Reduce max steps for striker vs. goalie (#4377 )	4 年前
GitHub	31919e08	[MLA-1267] Account for actuators in training and inference. (#4371 )	4 年前
GitHub	5457ff38	Update README.md (#4376 ) Adjusted readme to reflect new release	4 年前
GitHub	9cc4e0b2	update demonstration meta files (#4367 )	4 年前
GitHub	99ccb7b9	Merge pull request #4369 from Unity-Technologies/release_6-to-master Merge release 6 back into master	4 年前
GitHub	e7916b08	add pre-commit hook for dotnet-format (#4362 )	4 年前
GitHub	cf570f8c	Update barracuda in the hopes that our burst crashes go away. (#4359 ) (#4365 )	4 年前
GitHub	8bbcfc28	fix deleted observations (#4366 )	4 年前
GitHub	bb9417f7	Update example environments to use the Actuator API (#4363 )	4 年前
GitHub	134f548c	doc fix (#4354 )	4 年前
GitHub	19a80b1c	Fix null reference error when passing a null array to an action segment. (#4358 )	4 年前
GitHub	1f00faa5	Remove whitespace in markdown (#4357 )	4 年前
GitHub	e3bc3352	[pytorch] Add decoders, distributions, encoders, layers, networks, and utils (#4349 )	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
GitHub	25dc8c3d	Add Saver Class to handle all save/load/checkpoint/export work (#4323 )	4 年前
GitHub	3a7572b4	Integrate IActuators into ML-Agents core code. (#4315 ) Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
GitHub	76deba36	Merge pull request #4334 from Unity-Technologies/global-variables Adding rank to ml-agents	4 年前
Chris Elion	46d8b730	process->node	4 年前
Chris Elion	d2133d83	comments and cleanup	4 年前
GitHub	705a0e0e	Curriculum: If no behavior specified, do magic (#4346 ) * Make behavior in curriculum a required attrib * Re-adding the test	4 年前
Anupam Bhatnagar	abc1220f	Merge branch 'master' into global-variables	4 年前
GitHub	a74c7bc5	TensorBoard Lesson -> Lesson Number (#4347 )	4 年前
Anupam Bhatnagar	d3e8f124	removing horovod from tf policy	4 年前
GitHub	d363f1fa	fix changelog date (#4344 )	4 年前
Anupam Bhatnagar	87bdf353	[skip ci] save model on worker zero only	4 年前
GitHub	6799ea16	[MLA-1219] custom editor for RB Sensor (#4312 )	4 年前
Anupam Bhatnagar	a88e3273	removing horovod import	4 年前
GitHub	9dc1d99e	Initialize normalizer with mean/variance from first trajectory (#4299 ) Co-authored-by: Chris Elion <chris.elion@unity3d.com>	4 年前
Anupam Bhatnagar	a5cc4d03	Merge branch 'master' into global-variables	4 年前
GitHub	73f05eaa	add --upgrade to pip to get newer downloader (#4338 )	4 年前
Anupam Bhatnagar	7a25b882	adding globals	4 年前
GitHub	f1084775	rearrange stat logging to make it easier to modify (#4336 )	4 年前
Anupam Bhatnagar	dbd5dc04	adding rank to ml-agents	4 年前
GitHub	3f44a0bc	cleanup around AdamOptimizer (#4333 ) * cleanup around AdamOptimizer * methods to creat Optimizer instances	4 年前
GitHub	b20f877c	Update CHANGELOG.md for #4274 (#4308 ) * Update CHANGELOG.md Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>	4 年前

... 5 6 7 8 9 ...

479 次代码提交 (9bb905da-fce9-4ff5-a2f8-bc8b6ad10a98)