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 202db853 Remove unnecessary line (#4260) 4 年前
..
components [MLA-427] make pyupgrade convert f-strings too (#4244) 4 年前
ghost don't try/except for control flow (#4251) 4 年前
optimizer [refactor] Structure configuration files into classes (#3936) 5 年前
policy [MLA-427] make pyupgrade convert f-strings too (#4244) 4 年前
ppo [MLA-427] make pyupgrade convert f-strings too (#4244) 4 年前
sac Remove unnecessary line (#4260) 4 年前
tests [MLA-1172] Reduce calls to training_behaviors (#4259) 4 年前
trainer add pyupgrade to pre-commit and run (#4239) 4 年前
__init__.py Update version for release 4 (master) (#4207) 4 年前
action_info.py Move advance() logic for environment manager out of trainer_controller (#3234) 5 年前
agent_processor.py Don't drop multiple stats from the same step (#4236) 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 format files with pre-commit. 4 年前
cli_utils.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
demo_loader.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
distributions.py Hotfixes for Release 0.15.1 (#3698) 5 年前
env_manager.py [MLA-1172] Reduce calls to training_behaviors (#4259) 4 年前
environment_parameter_manager.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
exception.py Combined model and policy for PPO 5 年前
learn.py Convert checkpoints to .NN (#4127) 4 年前
models.py [MLA-427] make pyupgrade convert f-strings too (#4244) 4 年前
run_experiment.py [refactor] Structure configuration files into classes (#3936) 5 年前
settings.py don't allow --num-envs >1 with no --env (#4203) 4 年前
simple_env_manager.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
stats.py [MLA-427] make pyupgrade convert f-strings too (#4244) 4 年前
subprocess_env_manager.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
tensorflow_to_barracuda.py backport tf2bc changes from barracuda-release (#3341) 5 年前
trainer_controller.py Update add-fire to latest master, including Policy refactor (#4263) 4 年前
trainer_util.py Update add-fire to latest master, including Policy refactor (#4263) 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