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
253 提交
337 分支
128 Plastic标签
 
 
 
 
 
目录树: 05fc088d
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 '05fc088d'
${ noResults }
ml-agents/ml-agents/mlagents/trainers
GitHub 05fc088d [refactor] Don't compute grad for q2_p in SAC Optimizer (#4509) 4 年前
..
components [refactor] Move TF-specific files to tf/ folder (#4266) 4 年前
ghost Rename Saver to ModelSaver (#4402) 4 年前
model_saver Random Network Distillation for Torch (#4473) 4 年前
optimizer Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
policy Don't run value during policy evaluate, optimized soft update function (#4501) 4 年前
ppo Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
sac [refactor] Don't compute grad for q2_p in SAC Optimizer (#4509) 4 年前
tests [Bug-fix] RND would not be saved correctly. Added tests (#4514) 4 年前
tf [feature] Add small CNN for grids 5x5 and up (#4434) 4 年前
torch [Bug-fix] RND would not be saved correctly. Added tests (#4514) 4 年前
trainer Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
__init__.py update versions on master (#4469) 4 年前
action_info.py Move advance() logic for environment manager out of trainer_controller (#3234) 5 年前
agent_processor.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
behavior_id_utils.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
buffer.py [refactor] Optimize buffer sample_minibatch (#4508) 4 年前
cli_utils.py [feature] Fix TF tests, add --torch CLI option, allow run TF without torch installed (#4305) 4 年前
demo_loader.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
env_manager.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
environment_parameter_manager.py [add-fire] Merge post-0.19.0 master into add-fire (#4328) 4 年前
exception.py [add-fire] Merge post-0.19.0 master into add-fire (#4328) 4 年前
learn.py Make --torch use torch even without config (#4400) 4 年前
run_experiment.py [refactor] Structure configuration files into classes (#3936) 5 年前
settings.py Random Network Distillation for Torch (#4473) 4 年前
simple_env_manager.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
stats.py Merge branch 'master' into global-variables 4 年前
subprocess_env_manager.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
trainer_controller.py Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
trainer_util.py Make --torch use torch even without config (#4400) 4 年前
training_status.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
trajectory.py Renaming max_step to interrupted in TermialStep(s) (#3908) 5 年前
upgrade_config.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前