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
1089 提交
337 分支
128 Plastic标签
 
 
 
 
 
目录树: f7cb69de
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 'f7cb69de'
${ noResults }
ml-agents/ml-agents/mlagents/trainers
GitHub c613df3a Merge pull request #1922 from Unity-Technologies/release-v08-slowflag 6 年前
..
bc Merge pull request #1858 from Unity-Technologies/develop-esh-metrics 6 年前
ppo Adds SubprocessUnityEnvironment for parallel envs (#1751) 6 年前
tests Merge pull request #1922 from Unity-Technologies/release-v08-slowflag 6 年前
__init__.py Added logging per Brain of time to update policy, time elapsed during training, time to collect experiences, buffer length, average return 6 年前
action_info.py Move 'take_action' into Policy class (#1669) 6 年前
barracuda.py Barracuda integration into ML-Agents (#1557) 6 年前
buffer.py Fix for divide-by-zero error with Discrete Actions (#1520) 6 年前
curriculum.py Curriculum learning reward thresholding bug fix (#1141) 6 年前
demo_loader.py Move done and reward to buffer from demonstration 6 年前
exception.py Fixed imports, all tests are passing. 6 年前
learn.py Fix '--slow' flag after environment updates 6 年前
meta_curriculum.py Curriculum learning reward thresholding bug fix (#1141) 6 年前
models.py Split `mlagents` into two packages (#1812) 6 年前
policy.py Merge pull request #1765 from Unity-Technologies/release-v0.7 6 年前
tensorflow_to_barracuda.py Barracuda integration into ML-Agents (#1557) 6 年前
trainer.py Reorganize to make metrics collection more accurate 6 年前
trainer_controller.py Fix '--slow' flag after environment updates 6 年前
trainer_metrics.py Reorganize to make metrics collection more accurate 6 年前