Boosting Offline Reinforcement Learning with Residual Generative Modeling.

Hua Wei Deheng Ye Zhao Liu Hao Wu Bo Yuan Qiang Fu Wei Yang Zhenhui Li

Published in: CoRR (2021)

Keyphrases

reinforcement learning
data driven
learning algorithm
data sets
function approximation
real time
generative model
optimal policy
active learning
markov decision processes
learning problems