Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Bootstrapping Fitted Q-Evaluation for Off-Policy Inference

About

Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical property is less understood. In this paper, we study the use of bootstrapping in off-policy evaluation (OPE), and in particular, we focus on the fitted Q-evaluation (FQE) that is known to be minimax-optimal in the tabular and linear-model cases. We propose a bootstrapping FQE method for inferring the distribution of the policy evaluation error and show that this method is asymptotically efficient and distributionally consistent for off-policy statistical inference. To overcome the computation limit of bootstrapping, we further adapt a subsampling procedure that improves the runtime by an order of magnitude. We numerically evaluate the bootrapping method in classical RL environments for confidence interval estimation, estimating the variance of off-policy evaluator, and estimating the correlation between multiple off-policy evaluators.

Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesv\'ari, Mengdi Wang• 2021

Related benchmarks

TaskDatasetResultRank
Empirical Coverage EstimationRiverSwim
Q^π(1, 0)0.932
120
Empirical Coverage EstimationRiverSwim episode length T = 10 (nominal 95% coverage)
Q* (1, 0)86.2
20
Empirical Coverage EstimationRiverSwim T=50 90% nominal coverage
Q* (1, 0)84.3
20
Optimal Policy Recovery (Empirical Coverage)RiverSwim T=50 nominal 95% coverage
Q* Recovery (s=1, a=0)90.5
20
Action-Value coverage estimationRiverSwim mostly-right target policy T=50
Q-Value Estimate (s=1, a=0)0.474
20
State-Value coverage estimationRiverSwim mostly-right target policy T=50
V(s=1)0.474
20
Off-policy EvaluationRiverSwim mostly-left policy, T=50
Qπ(1, 0) Coverage50
20
State Value Estimation CoverageRiverSwim
Value Estimate State 10.931
20
State-Action Value Estimation CoverageRiverSwim
Q-Value Estimate (s=1, a=0)0.931
20
Action-Value coverage estimationRiverSwim T=100
Q*(1,0)0.854
15
Showing 10 of 13 rows

Other info

Follow for update