Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 
GitHub 6ae8ea1e [coma2] Add support for variable length obs in COMA2 (#5038) 4 年前
..
components [coma2] Make group extrinsic reward part of extrinsic (#5033) 4 年前
__init__.py [pytorch] Add decoders, distributions, encoders, layers, networks, and utils (#4349) 4 年前
action_flattener.py Action Model (#4580) 4 年前
action_log_probs.py Buffer key enums (#4907) 4 年前
action_model.py Develop hybrid action staging (#4702) 4 年前
agent_action.py Update v2-staging from main (March 15) (#5123) 4 年前
attention.py Silencing a Torch warning that raises when exporting the attention module to ONNX 4 年前
decoders.py Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
distributions.py Fix equation for entropy 4 年前
encoders.py Run pytest on GPU (#4865) 4 年前
layers.py add LayerNorm (#4847) 4 年前
model_serialization.py Adding a helper method for creating observation placeholder names and removed the _h and _c placeholders 4 年前
networks.py [coma2] Add support for variable length obs in COMA2 (#5038) 4 年前
utils.py [coma2] Add support for variable length obs in COMA2 (#5038) 4 年前