RORL: Robust Offline Reinforcement Learning via Conservative Smoothing.

Rui Yang Chenjia Bai Xiaoteng Ma Zhaoran Wang Chongjie Zhang Lei Han

Published in: NeurIPS (2022)

Keyphrases

reinforcement learning
function approximation
data sets
computer vision
multi agent
computationally efficient
multiscale
text classification
learning problems
model free
robust statistical