ml-agents

作者	SHA1	备注	提交日期
GitHub	c9c9e147	Revamp Crawler & Walker (#841 ) * Revamps agent code for walker and crawler environments to use shared JointDriveController system. * Crawler has been reworked to be very cute. * Crawler & Walker environments have been reworked to be visually consistent. * Added Dynamic Crawler scene. * All scenes re-trained and new models added. * Documentation changes.	6 年前
GitHub	88b917b3	[format] Format code whitespace with Unity Formatter. (#2550 )	5 年前
GitHub	f01dd1c1	[coding conventions] Change c# code to be compliant with Unity coding conventions. (#2555 )	5 年前
GitHub	2db09cef	Model override from commandline (#3265 ) * WIP model override from commandline * Agent lazy init, multiple overrides * MLAgentsExamples namespace * add model override to 3dball	4 年前
GitHub	1e0b022f	[MLA-850] rename namespaces to Unity.MLAgents (#3843 ) * rename in protos * rename in C# * doc changes, migration, changelog * PR numbers * fix standalone test path	4 年前
Hunter-Unity	3edca8d0	reduced maxAngVel, enabled enhanced determinism, cont spec	4 年前
Hunter-Unity	da6d25c9	updated walker dynamic demo file. cleanup	4 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
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
HH	35235345	add NaN check for reward manager. start vel penalty	4 年前
HH	281a4e60	add a NaN debug for action values	4 年前
HH	7c63197e	start dynamic cleanup and more debug for NaNs	4 年前
GitHub	e7916b08	add pre-commit hook for dotnet-format (#4362 )	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
HH	4d720feb	added trained 6 leg creature	4 年前

15 次代码提交 (c4c67218-5ea3-45b6-a22d-3091c20fa411)