Counterfactual off-policy evaluation with gumbel-max structural causal models
Name
oberst19a.pdf
Description
Published version
Size
1.42 MB
Format
Adobe PDF
Checksum (MD5)
634ebbd14d21945af3ff2baec0e558a5
Author(s)
Oberst, Michael
Sontag, David Alexander
Date Issued
June 2019
Journal
Proceedings of the 36th International Conference on Machine Learning
Publisher
MLResearch Press
Citation
Oberst, Michael and David Sontag. "Counterfactual off-policy evaluation with gumbel-max structural causal models." Proceedings of the 36th International Conference on Machine Learning, June 2019, Long Beach, California, MLResearch Press, 2019.
Version
Final published version
Abstract
We introduce an off-policy evaluation procedure for highlighting episodes where applying a reinforcement learned (RL) policy is likely to have produced a substantially different outcome than the observed policy. In particular, we introduce a class of structural causal models (SCMs) for generating counterfactual trajectories in finite partially observable Markov Decision Processes (POMDPs). We see this as a useful procedure for off-policy "debugging" in high-risk settings (e.g., healthcare); by decomposing the expected difference in reward between the RL and observed policy into specific episodes, we can identify episodes where the counterfactual difference in reward is most dramatic. This in turn can be used to facilitate review of specific episodes by domain experts. We demonstrate the utility of this procedure with a synthetic environment of sepsis management.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://proceedings.mlr.press/v97/
