Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
This addresses a practical gap in offline RL for scenarios with heterogeneous data sources, though it is incremental by extending existing theoretical frameworks to perturbed sources.
The paper tackles offline reinforcement learning with data from multiple perturbed sources rather than the target task itself, proposing the HetPEVI algorithm that achieves optimal performance up to a polynomial factor of the horizon length when sources collectively provide good data coverage.
Existing theoretical studies on offline reinforcement learning (RL) mostly consider a dataset sampled directly from the target task. In practice, however, data often come from several heterogeneous but related sources. Motivated by this gap, this work aims at rigorously understanding offline RL with multiple datasets that are collected from randomly perturbed versions of the target task instead of from itself. An information-theoretic lower bound is derived, which reveals a necessary requirement on the number of involved sources in addition to that on the number of data samples. Then, a novel HetPEVI algorithm is proposed, which simultaneously considers the sample uncertainties from a finite number of data samples per data source and the source uncertainties due to a finite number of available data sources. Theoretical analyses demonstrate that HetPEVI can solve the target task as long as the data sources collectively provide a good data coverage. Moreover, HetPEVI is demonstrated to be optimal up to a polynomial factor of the horizon length. Finally, the study is extended to offline Markov games and offline robust RL, which demonstrates the generality of the proposed designs and theoretical analyses.