Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
This addresses the need for standardized empirical analyses in safety-critical applications, though it is incremental as it focuses on benchmarking existing methods.
The paper tackles the problem of off-policy policy evaluation in reinforcement learning by providing an experimental benchmark and empirical study, resulting in a comprehensive benchmarking suite and summarized guidelines for practical use.
We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, there has been a flurry of recent proposals for OPE method, leading to a need for standardized empirical analyses. Our work takes a strong focus on diversity of experimental design to enable stress testing of OPE methods. We provide a comprehensive benchmarking suite to study the interplay of different attributes on method performance. We distill the results into a summarized set of guidelines for OPE in practice. Our software package, the Caltech OPE Benchmarking Suite (COBS), is open-sourced and we invite interested researchers to further contribute to the benchmark.