GitHub
5 年前
当前提交
0a163871
共有 71 个文件被更改,包括 9472 次插入 和 13486 次删除
-
2UnitySDK/Assets/ML-Agents/Editor/DemonstrationImporter.cs
-
601UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHardLearning.nn
-
509UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallLearning.nn
-
658UnitySDK/Assets/ML-Agents/Examples/BananaCollectors/TFModels/BananaLearning.nn
-
15UnitySDK/Assets/ML-Agents/Examples/Basic/TFModels/BasicLearning.nn
-
143UnitySDK/Assets/ML-Agents/Examples/Bouncer/TFModels/BouncerLearning.nn
-
3UnitySDK/Assets/ML-Agents/Examples/Crawler/Brains/CrawlerDynamicLearning.asset
-
3UnitySDK/Assets/ML-Agents/Examples/Crawler/Brains/CrawlerStaticLearning.asset
-
890UnitySDK/Assets/ML-Agents/Examples/Crawler/Prefabs/DynamicPlatform.prefab
-
810UnitySDK/Assets/ML-Agents/Examples/Crawler/Prefabs/FixedPlatform.prefab
-
965UnitySDK/Assets/ML-Agents/Examples/Crawler/Scenes/CrawlerDynamicTarget.unity
-
947UnitySDK/Assets/ML-Agents/Examples/Crawler/Scenes/CrawlerStaticTarget.unity
-
43UnitySDK/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs
-
1001UnitySDK/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamicLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStaticLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorldLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Hallway/TFModels/HallwayLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Pyramids/TFModels/PyramidsLearning.nn
-
572UnitySDK/Assets/ML-Agents/Examples/Reacher/TFModels/ReacherLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Soccer/TFModels/GoalieLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Soccer/TFModels/StrikerLearning.nn
-
522UnitySDK/Assets/ML-Agents/Examples/Tennis/TFModels/TennisLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Walker/TFModels/WalkerLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJumpLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJumpLearning.nn
-
31docs/Reward-Signals.md
-
1docs/Training-ML-Agents.md
-
4gym-unity/setup.py
-
8ml-agents-envs/mlagents/envs/subprocess_env_manager.py
-
7ml-agents-envs/mlagents/envs/tests/test_timers.py
-
63ml-agents-envs/mlagents/envs/timers.py
-
2ml-agents-envs/setup.py
-
2ml-agents/mlagents/trainers/bc/models.py
-
11ml-agents/mlagents/trainers/bc/offline_trainer.py
-
11ml-agents/mlagents/trainers/bc/online_trainer.py
-
16ml-agents/mlagents/trainers/bc/policy.py
-
33ml-agents/mlagents/trainers/bc/trainer.py
-
171ml-agents/mlagents/trainers/buffer.py
-
40ml-agents/mlagents/trainers/components/bc/module.py
-
179ml-agents/mlagents/trainers/components/reward_signals/curiosity/signal.py
-
19ml-agents/mlagents/trainers/components/reward_signals/extrinsic/signal.py
-
37ml-agents/mlagents/trainers/components/reward_signals/gail/model.py
-
260ml-agents/mlagents/trainers/components/reward_signals/gail/signal.py
-
39ml-agents/mlagents/trainers/components/reward_signals/reward_signal.py
-
8ml-agents/mlagents/trainers/components/reward_signals/reward_signal_factory.py
-
56ml-agents/mlagents/trainers/learn.py
-
258ml-agents/mlagents/trainers/models.py
-
243ml-agents/mlagents/trainers/ppo/models.py
-
225ml-agents/mlagents/trainers/ppo/policy.py
-
367ml-agents/mlagents/trainers/ppo/trainer.py
-
71ml-agents/mlagents/trainers/tests/mock_brain.py
-
71ml-agents/mlagents/trainers/tests/test_buffer.py
-
9ml-agents/mlagents/trainers/tests/test_learn.py
-
33ml-agents/mlagents/trainers/tests/test_ppo.py
-
65ml-agents/mlagents/trainers/tests/test_reward_signals.py
-
289ml-agents/mlagents/trainers/tests/test_trainer_controller.py
-
5ml-agents/mlagents/trainers/tf_policy.py
-
173ml-agents/mlagents/trainers/trainer.py
-
113ml-agents/mlagents/trainers/trainer_controller.py
-
5ml-agents/setup.py
-
208ml-agents/mlagents/trainers/ppo/multi_gpu_policy.py
-
286ml-agents/mlagents/trainers/rl_trainer.py
-
127ml-agents/mlagents/trainers/tests/test_multigpu.py
-
90ml-agents/mlagents/trainers/tests/test_rl_trainer.py
-
207ml-agents/mlagents/trainers/tests/test_simple_rl.py
-
315ml-agents/mlagents/trainers/tests/test_trainer_util.py
-
97ml-agents/mlagents/trainers/trainer_util.py
-
8UnitySDK/Assets/ML-Agents/Examples/Crawler/Prefabs/Crawler.prefab.meta
-
1001UnitySDK/Assets/ML-Agents/Examples/Crawler/Prefabs/Crawler.prefab
|
|||
vector_observation ���� - epsilon ���� action action_probs action_output_shape� ���� �? action_output_shape memory_size version_number is_continuous_control clip_by_value/y mul_3/x running_variance - - mul_2/x 3 normalization_steps 4 add_3/y 5 clip_by_value/Minimum/y 6 normalized_state/Minimum/y 7 log_sigma_squared 8 Log/x : truediv_3/y ; normalized_state/y < |