deep-reinforcement-learning

deep-reinforcement-learning

前言

方法

蒙特祖玛的复仇

第一人称射击游戏

SLAM-Augmented DQN

Direct Future Prediction

开放世界游戏

即时战略游戏

团队体育游戏

文字冒险游戏

开放的挑战

附录

Distributional RL

Policy Gradient

Imitation Learning and Inverse Reinforcement Learning

Transfer and Multitask RL

Powered by GitBook

For The Win

​Capture the Flag: the emergence of complex cooperative agents​

Direct Future Prediction

开放世界游戏

Last updated 2 years ago