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
 
 
 
 
 
Jonathan Harper 47893e9c minor tweaks 5 年前
..
bc When checking for the compatibility of the expert brain with the policy brain, we will remove the action descriptions from the dictionary of things we need to compare. This is to prevent the case where a user has different descriptions for his actions but still wants to train a brain using expert demonstrations. (#2517) 5 年前
components Fix crash with VAIL + GAIL (#2598) 5 年前
ppo minor tweaks 5 年前
sac minor tweaks 5 年前
tests Develop yaml json loading errors (#2601) 5 年前
__init__.py Fix flake8 import warnings (#2584) 5 年前
barracuda.py cleanup setup.cfg 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 Fix flake8 import warnings (#2584) 5 年前
exception.py Develop yaml json loading errors (#2601) 5 年前
learn.py EXPERIMENTAL horovod support 5 年前
meta_curriculum.py Python code reformat via [`black`](https://github.com/ambv/black). 6 年前
models.py Enable learning rate decay to be disabled (#2567) 5 年前
rl_trainer.py Fix flake8 import warnings (#2584) 5 年前
tensorflow_to_barracuda.py Barracuda hotfix for LSTM and tests (#2352) 5 年前
tf_policy.py EXPERIMENTAL horovod support 5 年前
trainer.py Fix flake8 import warnings (#2584) 5 年前
trainer_controller.py Fix flake8 import warnings (#2584) 5 年前
trainer_metrics.py Enable mypy in precommit checks (#2177) 6 年前
trainer_util.py Develop yaml json loading errors (#2601) 5 年前