Pith. sign in

REVIEW

Combining Parametric and Nonparametric Models for Off-Policy Evaluation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.05787 v2 pith:VYY4N65T submitted 2019-05-14 cs.LG stat.ML

classification cs.LGstat.ML
keywords approachmodelserrorestimateevaluationmodeloff-policyparametric
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate has the least expected error. We do so by first estimating the local accuracy of each model and then using a planner to select which model to use at every time step as to minimize the return error estimate along entire trajectories. Across a variety of domains, our mixture-based approach outperforms the individual models alone as well as state-of-the-art importance sampling-based estimators.

Discussion (0). Continue with ORCID to comment.

Pith tools