search

Lizhi-sjtu / DRL-code-pytorch

Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.
MIT License
1.1k stars 179 forks source link

PPO源代码错误问题 #9

Closed zcheng19 closed 1 year ago

zcheng19 commented 1 year ago

在PPO-discrete/PPO_discrete.py中的111行，gae = delta + self.gamma self.lamda gae (1.0 - d) 有问题，应该是 gae = gae + self.gamma self.lamda delta (1.0 - d) 吧