unity-tech-cn
/
ml-agents
46
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
35 提交
337 分支
128 Plastic标签
 
 
 
 
 
目录树: ef2dfd4c
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 'ef2dfd4c'
${ noResults }
ml-agents/ml-agents/mlagents/trainers
Andrew Cohen ef2dfd4c adjusting tests to expect trainer.add_policy to be called 5 年前
..
bc Split Buffer into processing and update buffers (#2964) 5 年前
components Split Buffer into processing and update buffers (#2964) 5 年前
ppo add_policy and create_policy separated 5 年前
sac add_policy and create_policy separated 5 年前
tests adjusting tests to expect trainer.add_policy to be called 5 年前
__init__.py bump version strings (#2955) 5 年前
agent_processor.py Split Buffer into processing and update buffers (#2964) 5 年前
barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
buffer.py Split Buffer into processing and update buffers (#2964) 5 年前
curriculum.py Develop side channels: migrate reset parameters (#2990) 5 年前
demo_loader.py Split Buffer into processing and update buffers (#2964) 5 年前
exception.py Develop yaml json loading errors (#2601) 5 年前
learn.py Develop side channels: migrate reset parameters (#2990) 5 年前
meta_curriculum.py Develop side channels: migrate reset parameters (#2990) 5 年前
models.py Allow usage with tensorflow 2.0.0 (via tf.compat.v1) (#2665) 5 年前
rl_trainer.py add_policy and create_policy separated 5 年前
tensorflow_to_barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
tf_policy.py Develop cold fix recurrent (#3032) 5 年前
trainer.py add_policy and create_policy separated 5 年前
trainer_controller.py adjusting tests to expect trainer.add_policy to be called 5 年前
trainer_metrics.py small mypy cleanup (#2637) 5 年前
trainer_util.py recieves brain_name and identifier on python side 5 年前