Timezone: »

 
Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
Cameron Voloshin · Hoang Le · Nan Jiang · Yisong Yue

@
in Dataset and Benchmark Poster Session 3 »
Event URL: https://openreview.net/forum?id=IsK8iKbL-I »

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.

[ Chat]  [ OpenReview] 

Author Information

Cameron Voloshin (California Institute of Technology)
Hoang Le (Microsoft Research)
Nan Jiang (University of Illinois at Urbana-Champaign)
Yisong Yue (Caltech)

More from the Same Authors