Robust Offline Reinforcement Learning with Heavy-Tailed Rewards.

Jin Zhu Runzhe Wan Zhengling Qi Shikai Luo Chengchun Shi

Published in: AISTATS (2024)

Keyphrases

reinforcement learning
heavy tailed
markov decision processes
generalized gaussian
heavy tails
image processing
pairwise
graph cuts
optimal policy
distance function