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 d6f69c1f handle null action outputs (#2988) 5 年前
..
bc Fix batch size issue with BC (#2965) 5 年前
components Fix bug where constant LR in pretraining will throw TF error (#2977) 5 年前
ppo Develop remove past action communication (#2913) 5 年前
sac Develop remove past action communication (#2913) 5 年前
tests Fix bug where constant LR in pretraining will throw TF error (#2977) 5 年前
__init__.py bump version strings (#2955) 5 年前
barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
buffer.py Fix flake8 import warnings (#2584) 5 年前
curriculum.py Develop yaml json loading errors (#2601) 5 年前
demo_loader.py add timers and fix filehandle leak (#2989) 5 年前
exception.py Develop yaml json loading errors (#2601) 5 年前
learn.py Allow --version argument in mlagents-learn (#2942) 5 年前
meta_curriculum.py check for unecessary list comprehensions (#2707) 5 年前
models.py Allow usage with tensorflow 2.0.0 (via tf.compat.v1) (#2665) 5 年前
rl_trainer.py Develop remove past action communication (#2913) 5 年前
tensorflow_to_barracuda.py fix errors from new flake8-comprehensions (#2917) 5 年前
tf_policy.py Develop remove past action communication (#2913) 5 年前
trainer.py Bubbled up indexing of AllBrainInfo to trainer controller from trainers 5 年前
trainer_controller.py handle null action outputs (#2988) 5 年前
trainer_metrics.py small mypy cleanup (#2637) 5 年前
trainer_util.py Develop spawn brains (#2676) 5 年前