ml-agents

作者	SHA1	备注	提交日期
GitHub	ea0c6fa0	[WIP] Side Channel Design Changes (#3807 ) * Make EnvironmentParameters a first-class citizen in the API Missing: Python conterparts and testing. * Minor comment fix to Engine Parameters * A second minor fix. * Make EngineConfigChannel Internal and add a singleton/sealed accessor * Make StatsSideChannel Internal and add a singleton/sealed accessor * Changes to SideChannelUtils - Disallow two sidechannels of the same type to be added - Remove GetSideChannels that return a list as that is now unnecessary - Make most methods except (register/unregister) internal to limit users impacting the “system-level” side channels - Add an improved comment to SideChannel.cs * Added Dispose methods to system-level sidechannel wrappers - Specifically to StatsRecorder, EnvironmentParameters and EngineParameters. - Updated Academy.Dispose to take advantage of these. - Updated Editor tests to cover all three “system-level” side channels. Kudos to Unit Tests (TestAcade...	5 年前
GitHub	4399e29f	UI for Ray stacks, rename WriteAdapter to ObservationWriter (#3834 ) * UI for Ray stacks, rename WriteAdapter to ObservationWriter * move test * changelog and migration	5 年前
GitHub	adffe563	remove redundant demo files (#3837 )	5 年前
GitHub	f8909ab1	Add New 3 Joint Ragdoll Worm Environment (#3798 ) Co-authored-by: Arthur Juliani <awjuliani@gmail.com>	5 年前
GitHub	0a7e53be	Code Style - apply PascalCase (#3828 ) * cleanup a few classes * cleanup raycast code * more capitalization * more renames * changelog and migration * fix MaxStep in docs * doc string	5 年前
GitHub	256431f7	Doc review (#3803 ) * Edit and review package docs. * Filter out testa and internal namespaces. * remove offsetStep field that was accidentally revivified * Resolving review comments * Update com.unity.ml-agents/Runtime/Agent.cs * fix trailing whitespace * Revised Agent class intro and step description * Fixed a few missed comments. * removed prerelease warning Co-authored-by: Chris Elion <chris.elion@unity3d.com>	5 年前
GitHub	3a4a6792	access to observations in Heuristic (#3825 ) * access to observations in Heuristic * changelog	5 年前
GitHub	92b571e7	find and replace for ML-Agents Toolkit (#3799 ) * find and replace for ML-Agents Toolkit * apply * install ruby * apt-get update * Update config.yml	5 年前
GitHub	e33a343c	inference seed, increment seed for ModelRunner (#3823 ) * inference seed, increment seed for ModelRunner * changelog	5 年前
GitHub	023ba14f	[bug-fix] Fix stall in ghost trainer non-threaded (#3824 )	5 年前
Ervin Teng	392fcb4e	Fix stall in ghost trainer non-threaded	5 年前
GitHub	adeb6536	Catch dimension mismatches between demos and policy (#3821 )	5 年前
Ervin Teng	eef0d21a	Update comment	5 年前
GitHub	ccd40ce7	[bug-fix] Bugfixes for Threaded Trainers (#3817 )	5 年前
Ervin Teng	744db929	Adjust yield timeout	5 年前
GitHub	78f4da76	Making Gym a wrapper (#3812 ) * Making Gym a wrapper * Readding no graphics to the run gym test * typo * Modifying the changelog and the migrating doc * Applying pre-commit * [skip ci] Update gym-unity/gym_unity/tests/test_gym.py Co-Authored-By: Chris Elion <chris.elion@unity3d.com> * Adding a note that the BaseEnv will close when the wrapper closes * FoRgOt To rUn PrE-ComMiT Co-authored-by: Chris Elion <chris.elion@unity3d.com>	5 年前
Ervin Teng	ebed4f51	Only create/start thread for new trainers	5 年前
GitHub	70cbf48a	[docs] Fix pre-commit. (#3819 )	5 年前
Ervin Teng	6fa7ad0b	Avoid stall when multiple brains are present	5 年前
GitHub	6cbb238f	[docs] Call out platform limitations in our docs. (#3818 )	5 年前
GitHub	576ebc67	Fixing package validation errors. (#3808 ) * Fixing package validation errors. This impacts our API as two public variables have been made private. TODO: fix our CI to catch these automatically, per commit. * Changelog changes.	5 年前
GitHub	7e5513a4	[bug-fix] Increase buffer size for SAC tests (#3813 )	5 年前
GitHub	4d23200b	[refactor] Run Trainers in separate threads (#3690 )	5 年前

23 次代码提交 (ea0c6fa0-ded2-4d1d-a205-7ed73d5c3e13)