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: IJCAI (2021)

Keyphrases

reinforcement learning
learning algorithm
ensemble methods
generative model
feature selection
state space
semisupervised learning
neural network
training data
multi agent systems
learning process
text classification
expectation maximization
markov decision process
probabilistic topic models