activity
20222026
most citedDouble Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

2 citations · 4 across the 9 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

stat.ML2022★ 2 cited

Statistical Estimation of Confounded Linear MDPs: An Instrumental Variable Approach

Miao Lu, Wenhao Yang, Liangyu Zhang +1

In an Markov decision process (MDP), unobservable confounders may exist and have impacts on the data generating process, so that the classic off-policy evaluation (OPE) estimators…

cs.LG2022

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes

Miao Lu, Yifei Min, Zhaoran Wang +1

We study offline reinforcement learning (RL) in partially observable Markov decision processes. In particular, we aim to learn an optimal policy from a dataset collected by a behav…