unity-tech-cn
/
ml-agents
45
14
派生 39
代码 合并请求 版本发布
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
390 提交
337 分支
128 Plastic标签
 
 
 
 
 
目录树: 36cc4665
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 '36cc4665'
${ noResults }
ml-agents/ml-agents/mlagents/trainers/torch
vincentpierre 36cc4665 Removing some vis and vec fields from policy.py 4 年前
..
components Merge pull request #4734 from Unity-Technologies/develop-obs-as-list 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 Action Model (#4580) 4 年前
action_model.py Develop hybrid action staging (#4702) 4 年前
agent_action.py Merge master into hybrid actions staging branch (#4704) 4 年前
decoders.py Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
distributions.py Fix model inference issue with Barracuda v1.2.1 (#4766) (#4768) 4 年前
encoders.py [WIP] Refactor trainers to use list of obs rather than vec and vis obs 4 年前
layers.py Merge master into hybrid actions staging branch (#4704) 4 年前
model_serialization.py Removing some vis and vec fields from policy.py 4 年前
networks.py Made a nicer comment 4 年前
utils.py Solving merge conflicts 4 年前