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 43696d60 Fix bug in add_rewards_output and add test (#2442) 5 年前
..
bc Merge pull request #2421 from Unity-Technologies/hotfix-v0.9.1 5 年前
components Modification of reward signals and rl_trainer for SAC (#2433) 5 年前
ppo Fix bug in add_rewards_output and add test (#2442) 5 年前
tests Fix bug in add_rewards_output and add test (#2442) 5 年前
__init__.py Add environment manager for parallel environments (#2209) 6 年前
barracuda.py cleanup setup.cfg 6 年前
buffer.py Refactor Trainer and Model (#2360) 5 年前
curriculum.py Python code reformat via [`black`](https://github.com/ambv/black). 6 年前
demo_loader.py GAIL and Pretraining (#2118) 6 年前
exception.py Enable generalization training (#2232) 6 年前
learn.py Merge latest develop 5 年前
meta_curriculum.py Python code reformat via [`black`](https://github.com/ambv/black). 6 年前
models.py Refactor Trainer and Model (#2360) 5 年前
rl_trainer.py Modification of reward signals and rl_trainer for SAC (#2433) 5 年前
tensorflow_to_barracuda.py Barracuda hotfix for LSTM and tests (#2352) 5 年前
tf_policy.py Add Multi-GPU implementation for PPO (#2288) 5 年前
trainer.py Refactor Trainer and Model (#2360) 5 年前
trainer_controller.py Move trainer initialization into a utility function (#2412) 5 年前
trainer_metrics.py Enable mypy in precommit checks (#2177) 6 年前
trainer_util.py Move trainer initialization into a utility function (#2412) 5 年前