pith. sign in

arxiv: 2209.06620 · v3 · pith:BWORDNSRnew · submitted 2022-09-14 · 💻 cs.LG · cs.AI· stat.ML

Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation

classification 💻 cs.LG cs.AIstat.ML
keywords environmentapproximationdatasetdistributionallyfunctionlinearpolicyrobust
0
0 comments X
read the original abstract

Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the training environment (e.g., a simulator). This paper attempts to address these issues simultaneously with distributionally robust offline RL, where we learn a distributionally robust policy using historical data obtained from the source environment by optimizing against a worst-case perturbation thereof. In particular, we move beyond tabular settings and consider linear function approximation. More specifically, we consider two settings, one where the dataset is well-explored and the other where the dataset has sufficient coverage of the optimal policy. We propose two algorithms~-- one for each of the two settings~-- that achieve error bounds $\tilde{O}(d^{1/2}/N^{1/2})$ and $\tilde{O}(d^{3/2}/N^{1/2})$ respectively, where $d$ is the dimension in the linear function approximation and $N$ is the number of trajectories in the dataset. To the best of our knowledge, they provide the first non-asymptotic results of the sample complexity in this setting. Diverse experiments are conducted to demonstrate our theoretical findings, showing the superiority of our algorithm against the non-robust one.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.