浏览代码
Merge pull request #3441 from Unity-Technologies/master-into-release-0.14.0
Merge pull request #3441 from Unity-Technologies/master-into-release-0.14.0
Master into release 0.14.0 copy/asymm-envs
GitHub
5 年前
当前提交
9a4b151c
共有 42 个文件被更改,包括 6546 次插入 和 7578 次删除
-
496Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBall.nn
-
622Project/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHard.nn
-
14Project/Assets/ML-Agents/Examples/Basic/TFModels/Basic.nn
-
138Project/Assets/ML-Agents/Examples/Bouncer/TFModels/Bouncer.nn
-
1001Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamic.nn
-
1001Project/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStatic.nn
-
82Project/Assets/ML-Agents/Examples/FoodCollector/Prefabs/FoodCollectorArea.prefab
-
62Project/Assets/ML-Agents/Examples/FoodCollector/Prefabs/VisualFoodCollectorArea.prefab
-
660Project/Assets/ML-Agents/Examples/FoodCollector/TFModels/FoodCollector.nn
-
1001Project/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorld.nn
-
1001Project/Assets/ML-Agents/Examples/Hallway/TFModels/Hallway.nn
-
1001Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlock.nn
-
1001Project/Assets/ML-Agents/Examples/Pyramids/TFModels/Pyramids.nn
-
524Project/Assets/ML-Agents/Examples/Reacher/TFModels/Reacher.nn
-
1001Project/Assets/ML-Agents/Examples/Soccer/TFModels/Soccer.nn
-
1001Project/Assets/ML-Agents/Examples/Tennis/TFModels/Tennis.nn
-
1001Project/Assets/ML-Agents/Examples/Walker/TFModels/Walker.nn
-
1001Project/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJump.nn
-
1001Project/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJump.nn
-
38README.md
-
33com.unity.ml-agents/CHANGELOG.md
-
1com.unity.ml-agents/Runtime/Academy.cs
-
3com.unity.ml-agents/Runtime/Agent.cs
-
8com.unity.ml-agents/Runtime/InferenceBrain/GeneratorImpl.cs
-
43com.unity.ml-agents/Tests/Editor/MLAgentsEditModeTest.cs
-
4com.unity.ml-agents/package.json
-
13docs/Learning-Environment-Design-Agents.md
-
2docs/Learning-Environment-Examples.md
-
6docs/Migrating.md
-
12docs/Readme.md
-
4docs/Training-Curriculum-Learning.md
-
127gym-unity/gym_unity/envs/__init__.py
-
2gym-unity/gym_unity/tests/test_gym.py
-
45ml-agents/mlagents/trainers/agent_processor.py
-
2ml-agents/mlagents/trainers/buffer.py
-
2ml-agents/mlagents/trainers/learn.py
-
2ml-agents/mlagents/trainers/rl_trainer.py
-
3ml-agents/mlagents/trainers/tests/mock_brain.py
-
116ml-agents/mlagents/trainers/tests/test_agent_processor.py
-
2ml-agents/mlagents/trainers/tests/test_buffer.py
-
30ml-agents/mlagents/trainers/tests/test_rl_trainer.py
-
17utils/make_readme_table.py
|
|||
vector_observation ���� epsilon ���� action action_probs action_output_shape� ���� �? action_output_shape memory_size version_number is_continuous_control mul_3/x mul_2/x truediv_3/y mul_4/x Log/x running_variance normalization_steps clip_by_value/Minimum/y log_sigma_squared add_4/y running_mean normalized_state/Minimum/y clip_by_value/y normalized_state/y |