2 papers
cs.LG2024
MoMA: Model-based Mirror Ascent for Offline Reinforcement Learning
Mao Hong, Zhiyue Zhang, Yue Wu +1
Model-based offline reinforcement learning methods (RL) have achieved state-of-the-art performance in many decision-making problems thanks to their sample efficiency and generaliza…
stat.ML2023
A Policy Gradient Method for Confounded POMDPs
Mao Hong, Zhengling Qi, Yanxun Xu
In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offlin…