GitHub
6 年前
当前提交
2d1bda57
共有 161 个文件被更改,包括 8607 次插入 和 7091 次删除
-
17.circleci/config.yml
-
3.gitignore
-
8Dockerfile
-
4README.md
-
29UnitySDK/Assets/ML-Agents/Editor/AgentEditor.cs
-
2UnitySDK/Assets/ML-Agents/Editor/BrainParametersDrawer.cs
-
1001UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHardLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallLearning.nn
-
6UnitySDK/Assets/ML-Agents/Examples/BananaCollectors/Scripts/BananaAgent.cs
-
622UnitySDK/Assets/ML-Agents/Examples/BananaCollectors/TFModels/BananaLearning.nn
-
22UnitySDK/Assets/ML-Agents/Examples/Basic/TFModels/BasicLearning.nn
-
272UnitySDK/Assets/ML-Agents/Examples/Bouncer/TFModels/BouncerLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerDynamicLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Crawler/TFModels/CrawlerStaticLearning.nn
-
306UnitySDK/Assets/ML-Agents/Examples/GridWorld/Scenes/GridWorld.unity
-
5UnitySDK/Assets/ML-Agents/Examples/GridWorld/Scenes/GridWorld.unity.meta
-
10UnitySDK/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs
-
997UnitySDK/Assets/ML-Agents/Examples/GridWorld/TFModels/GridWorldLearning.nn
-
999UnitySDK/Assets/ML-Agents/Examples/Hallway/TFModels/HallwayLearning.nn
-
1000UnitySDK/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockLearning.nn
-
1000UnitySDK/Assets/ML-Agents/Examples/Pyramids/TFModels/PyramidsLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/Reacher/TFModels/ReacherLearning.nn
-
100UnitySDK/Assets/ML-Agents/Examples/SharedAssets/Scripts/RayPerception.cs
-
2UnitySDK/Assets/ML-Agents/Examples/SharedAssets/Scripts/RayPerception.cs.meta
-
75UnitySDK/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccer.cs
-
4UnitySDK/Assets/ML-Agents/Examples/Soccer/Scripts/SoccerBallController.cs
-
48UnitySDK/Assets/ML-Agents/Examples/Soccer/Scripts/SoccerFieldArea.cs
-
1UnitySDK/Assets/ML-Agents/Examples/Tennis/Scripts/TennisArea.cs
-
1001UnitySDK/Assets/ML-Agents/Examples/Tennis/TFModels/TennisLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/WallJump/TFModels/BigWallJumpLearning.nn
-
1001UnitySDK/Assets/ML-Agents/Examples/WallJump/TFModels/SmallWallJumpLearning.nn
-
101UnitySDK/Assets/ML-Agents/Scripts/Academy.cs
-
120UnitySDK/Assets/ML-Agents/Scripts/Agent.cs
-
1UnitySDK/Assets/ML-Agents/Scripts/Batcher.cs
-
25UnitySDK/Assets/ML-Agents/Scripts/Brain.cs
-
49UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/AgentActionProto.cs
-
57UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/AgentInfoProto.cs
-
2UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/BrainParametersProto.cs
-
53UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/EnvironmentParametersProto.cs
-
16UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/UnityInput.cs
-
24UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/UnityMessage.cs
-
16UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/UnityOutput.cs
-
8UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/UnityRlInitializationOutput.cs
-
10UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/UnityRlInput.cs
-
13UnitySDK/Assets/ML-Agents/Scripts/CommunicatorObjects/UnityToExternalGrpc.cs
-
5UnitySDK/Assets/ML-Agents/Scripts/InferenceBrain/BarracudaModelParamLoader.cs
-
20UnitySDK/Assets/ML-Agents/Scripts/InferenceBrain/GeneratorImpl.cs
-
4UnitySDK/Assets/ML-Agents/Scripts/InferenceBrain/ModelParamLoader.cs
-
2UnitySDK/Assets/ML-Agents/Scripts/InferenceBrain/TFSharpInferenceEngine.cs
-
3UnitySDK/Assets/ML-Agents/Scripts/InferenceBrain/Utils/Multinomial.cs
-
4UnitySDK/Assets/ML-Agents/Scripts/LearningBrain.cs
-
2docs/Basic-Guide.md
-
66docs/Installation-Windows.md
-
39docs/Installation.md
-
78docs/Learning-Environment-Design-Agents.md
-
2docs/Learning-Environment-Examples.md
-
34docs/Migrating.md
-
3docs/Readme.md
-
12docs/Training-ML-Agents.md
-
213docs/images/agent.png
-
302docs/images/visual-observation.png
-
2gym-unity/README.md
-
4gym-unity/setup.py
-
7ml-agents/mlagents/trainers/__init__.py
-
3ml-agents/mlagents/trainers/bc/offline_trainer.py
-
3ml-agents/mlagents/trainers/bc/online_trainer.py
-
31ml-agents/mlagents/trainers/bc/trainer.py
-
98ml-agents/mlagents/trainers/learn.py
-
2ml-agents/mlagents/trainers/models.py
-
24ml-agents/mlagents/trainers/policy.py
-
2ml-agents/mlagents/trainers/ppo/models.py
-
63ml-agents/mlagents/trainers/ppo/trainer.py
-
95ml-agents/mlagents/trainers/trainer.py
-
116ml-agents/mlagents/trainers/trainer_controller.py
-
6ml-agents/setup.py
-
2protobuf-definitions/README.md
-
2protobuf-definitions/make.bat
-
2protobuf-definitions/make_for_win.bat
-
3protobuf-definitions/proto/mlagents/envs/communicator_objects/agent_action_proto.proto
-
3protobuf-definitions/proto/mlagents/envs/communicator_objects/agent_info_proto.proto
-
3protobuf-definitions/proto/mlagents/envs/communicator_objects/environment_parameters_proto.proto
-
4gym-unity/gym_unity/tests/test_gym.py
-
5ml-agents-envs/mlagents/envs/rpc_communicator.py
-
88ml-agents-envs/mlagents/envs/environment.py
-
25ml-agents-envs/mlagents/envs/communicator_objects/unity_rl_output_pb2.py
-
29ml-agents-envs/mlagents/envs/communicator_objects/unity_rl_input_pb2.py
-
18ml-agents-envs/mlagents/envs/communicator_objects/unity_rl_initialization_output_pb2.py
-
10ml-agents-envs/mlagents/envs/communicator_objects/unity_rl_initialization_input_pb2.py
-
12ml-agents-envs/mlagents/envs/communicator_objects/unity_output_pb2.py
-
14ml-agents-envs/mlagents/envs/communicator_objects/unity_message_pb2.py
-
12ml-agents-envs/mlagents/envs/communicator_objects/unity_input_pb2.py
-
12ml-agents-envs/mlagents/envs/communicator_objects/space_type_proto_pb2.py
-
14ml-agents-envs/mlagents/envs/communicator_objects/resolution_proto_pb2.py
-
12ml-agents-envs/mlagents/envs/communicator_objects/header_pb2.py
-
41ml-agents-envs/mlagents/envs/communicator_objects/environment_parameters_proto_pb2.py
-
20ml-agents-envs/mlagents/envs/communicator_objects/engine_configuration_proto_pb2.py
-
1ml-agents-envs/mlagents/envs/communicator_objects/demonstration_meta_proto_pb2.py
-
14ml-agents-envs/mlagents/envs/communicator_objects/command_proto_pb2.py
-
24ml-agents-envs/mlagents/envs/communicator_objects/brain_parameters_proto_pb2.py
-
48ml-agents-envs/mlagents/envs/communicator_objects/agent_info_proto_pb2.py
1001
UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallHardLearning.nn
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
1001
UnitySDK/Assets/ML-Agents/Examples/3DBall/TFModels/3DBallLearning.nn
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
622
UnitySDK/Assets/ML-Agents/Examples/BananaCollectors/TFModels/BananaLearning.nn
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
|
|||
vector_observation ���� action_masks ���� action_probs concat_1 action value_estimate strided_slice_1/stack_2� ���� �? strided_slice_1/stack_2 strided_slice_1/stack_1� ���� �? strided_slice_1/stack_1 strided_slice_1/stack� ���� �? strided_slice_1/stack strided_slice/stack_2� ���� �? strided_slice/stack_2 strided_slice/stack_1� ���� �? strided_slice/stack_1 strided_slice/stack� ���� �? strided_slice/stack |
|||
|