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
96 提交
337 分支
128 Plastic标签
 
 
 
 
 
目录树: e2b2f4be
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 'e2b2f4be'
${ noResults }
ml-agents/ml-agents/mlagents/trainers
Ervin Teng e2b2f4be Address AgentProcessor comments 5 年前
..
bc Add way to check if trajectory is done or max_reached 5 年前
components Merge branch 'master' into develop-agentprocessor 5 年前
ppo Add way to check if trajectory is done or max_reached 5 年前
sac Add way to check if trajectory is done or max_reached 5 年前
tests Make conversion methods part of NamedTuples 5 年前
__init__.py bump version strings (#2955) 5 年前
action_info.py Remove {text,custom} {action,observations} (#2839) 5 年前
agent_processor.py Address AgentProcessor comments 5 年前
barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
brain.py Develop new ll api (#3022) 5 年前
brain_conversion_utils.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
buffer.py Move some common logic to buffer class 5 年前
curriculum.py Develop side channels: migrate reset parameters (#2990) 5 年前
demo_loader.py Merge branch 'master' into develop-agentprocessor 5 年前
env_manager.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
exception.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
learn.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
meta_curriculum.py Develop side channels: migrate reset parameters (#2990) 5 年前
models.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
policy.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
rl_trainer.py Properly report value estimates and episode length 5 年前
sampler_class.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
simple_env_manager.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
subprocess_env_manager.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
tensorflow_to_barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
tf_policy.py Make conversion methods part of NamedTuples 5 年前
trainer.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
trainer_controller.py Merge branch 'master' into develop-agentprocessor 5 年前
trainer_metrics.py small mypy cleanup (#2637) 5 年前
trainer_util.py Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
trajectory.py Add docstring 5 年前