Wei-Cheng Lee

https://github.com/uvipen/Super-mario-bros-PPO-pytorch/blob/ab4248d715346c6adc33c2157455e2b98c130bcc/train.py#L119 It should be ``` gae = gae * opt.gamma * opt.tau*(1 - done) ``` Suppose worker 1 has to sample 500 steps. The game prematurely ends at 250 steps,...

Can't understand reward scaling in value clipping of PPO

8

https://github.com/DLR-RM/stable-baselines3/blob/5a70af8abddfc96eac3911e69b20f19f5220947c/stable_baselines3/ppo/ppo.py#L231 Hi, I'm new to PPO. I can't understand why in your code, you say value clipping is related to reward scaling. I think you just clip the value ,...