Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
1.23k
stars
263
forks
source link
remove reinforce pong spec to prevent confusion #499
Closed
kengz closed 2 years ago
remove reinforce_pong spec
REINFORCE is an episodic algorithm that cannot be parallelized. It also cannot solve Atari games. Remove the
reinforce_pong
spec to prevent confusion.