rl-tutorials icon indicating copy to clipboard operation
rl-tutorials copied to clipboard
verified publisher icon johnjim0816

PPO.py里的140行是不是写错了

Open hykon123 opened this issue 3 years ago • 0 comments

PPO.py里的140行是不是写错了，returns = advantage(batch) + values[batch] ，为什么是advantage，而不是reward

hykon123 avatar May 21 '22 09:05 hykon123