ml-agents

作者	SHA1	备注	提交日期
GitHub	c315979f	Add command-line flag for example env scene selection (#3473 ) The Startup scene used for us to retrain and bundle example scenes together already accepts the SCENE_NAME environment variable to choose a scene. This change adds support for command-line selection of the scene name so that `--env-args` can be used to choose the scene. If both the environment variable and command-line flag are provided, the scene will use the environment variable.	4 年前
GitHub	0f381ab9	Remove ForceReset from Agent. (#3575 )	4 年前
GitHub	7697492d	Added missing docstrings (#3577 )	4 年前
GitHub	2a630030	[change] public SensorComponent fields to properties, add custom editor (#3564 )	4 年前
GitHub	9d9c8a8a	Merge pull request #3576 from Unity-Technologies/develop-shortentrainerconfigs [change] Reduce max_steps for PushBlock and Bouncer	4 年前
GitHub	11ff1553	unit tests for RenderTextureSensor+component (#3569 )	4 年前
GitHub	251aa7b3	Removed the IFloatProperties interface (#3570 ) * [skip ci] Remove IFloatProperties interface * [skip ci] Update the examples * Updating the documentation	4 年前
GitHub	9ae290ee	Messages will be consumed when the side channel registers (#3573 ) * Messages will be consumed when the side channel registers * addressing the comment * Update com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs Co-Authored-By: Chris Elion <chris.elion@unity3d.com> Co-authored-by: Chris Elion <celion@gmail.com>	4 年前
GitHub	c0e88aa8	Made BehaviorType public and added the SetBehaviorType method (#3572 ) * Made BehaviorType public and added the SetBehaviorType method * Moving the comments around and making Setting the behaviorType to the same value do nothing	4 年前
GitHub	91bbcabb	Added a numberOfActions get property on the BrainParameters (#3571 ) * Added a numberOfActions get property on the BrainParameters * forgot one place to replace * [skip ci] numberOfActions --> numActions	4 年前
GitHub	35df5d95	remove Use Heuristic from docs (#3568 )	4 年前
GitHub	4ba47a07	Fix timer name (#3562 )	4 年前
GitHub	529214e7	Caching side channel data for one step (#3565 ) * Caching side channel data for one step * [skip ci] Update com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs Co-Authored-By: Chris Elion <chris.elion@unity3d.com> Co-authored-by: Chris Elion <celion@gmail.com>	4 年前
Anupam Bhatnagar	e8e0078e	first commit	4 年前
GitHub	7100ae1a	Rename 2 documentation files (#3567 ) * 2 file renames Installation-Windows —> Installation-Anacondo-Windows to be clearer that it’s about Anaconda on Windows and not just Windows. index.md —> com.unity.ml-agents.md to be inline with package requirements.	4 年前
GitHub	86141eee	Merge pull request #3560 from Unity-Technologies/new-logger Add timestamps to logs	4 年前
Anupam Bhatnagar	c2611126	uniformize log level for all loggers	4 年前
Anupam Bhatnagar	ee67c628	add log level as an argument to create logger	4 年前
Anupam Bhatnagar	f4dbedcf	removed extraneous logging imports and loggers	4 年前
GitHub	cb153a0f	[change] Change warning language when adversarial scene is used without self-play (#3561 )	4 年前
Anupam Bhatnagar	abc369a6	Adding a logging utility for improved logs	4 年前
Ervin Teng	c3ff4a31	Cut bouncer max steps	4 年前
GitHub	6b7155e4	Develop package docs (#3551 ) * Improvements to the main repo Readme: put an emphasis on the Releases section. * Improving the installation guide. * Added the first draft of package readme.	4 年前
Anupam Bhatnagar	8f4999d4	Adding a logging utility for improved logs	4 年前
Ervin Teng	c825f13e	Reduce PushBlock max_steps	4 年前
GitHub	213d2466	[bug-fix] Change Simple1DEnvironment to spawn new agent IDs on reset (#3558 )	4 年前
GitHub	bcce774f	[tests] Visual observation tests (#3549 )	4 年前
GitHub	104c33e1	Made the decision requester internal and renamed RepeatAction (#3555 ) * [skip ci] made the decision requester internal and renamed RepeatAction * [skip ci] Updated the migration * Update com.unity.ml-agents/Runtime/DecisionRequester.cs Co-Authored-By: Chris Elion <chris.elion@unity3d.com> * Run tests Co-authored-by: Chris Elion <celion@gmail.com>	4 年前
GitHub	aad9d8a1	fix Demonstration tests (#3554 ) * fix Demonstration tests * handle null compressed obs in GetObservationProto * throw exception if sensor.GetCompressedObservation returns null	4 年前
GitHub	47755a62	Made BehaviorParameters internal (#3546 ) * Made the BrainParameters internal * Editing the docs * [skip-ci] A lot more controversial * [skip ci] Added formerly serialized as * Use cached BehaviorParameters	4 年前
GitHub	c5dd3641	Made Brain Parameters internal (#3545 ) * Made the BrainParameters internal * Editing the docs	4 年前
GitHub	a27117a4	Step sensor for Heuristic policy (#3542 )	4 年前
GitHub	870338b4	[bug-fix] Fix issue with more than one continuous actions (#3547 )	4 年前
GitHub	e5108d2c	Communication protocol versioning (#3535 )	4 年前
GitHub	323f104c	[tests] LSTM end-to-end tests (#3544 )	4 年前
GitHub	4e747130	Renaming AgentInfo.actionMasks to AgentInfo.DiscreteActionMasks (#3539 )	4 年前
GitHub	a6bf50db	Revert obs to goal in simple 1d test (#3540 )	4 年前
GitHub	6a49f608	develop-MLA-611-check-init (#3541 )	4 年前
GitHub	e4177de0	[change] Organize trainer files a bit better (#3538 )	4 年前
GitHub	f469cbb0	Simple1DEnv refactor and additional ghost trainer tests (#3537 )	4 年前
GitHub	e7ec5007	[change] Make Agent non-abstract, update Basic scene. (#3528 )	4 年前
GitHub	b9bd4df2	Modified some namespaces (#3533 ) * Added the MLAgents.Demonstrations namespace * Added the MLAgents.Editor namespace * Overrided the .demo.meta files due to the change in namespace * More namespace changes * Added the sidechannels namespace * Modified changelog and migrating docs	4 年前

42 次代码提交 (c315979f-94d7-401c-804e-d00ab3ac8200)