paper-with-me

홈 › Papers

CoinDICE: Off-Policy Confidence Interval Estimation

2020-10-22 · NeurIPS 2020 12 · Bo Dai, Ofir Nachum, Yinlam Chow, Lihong Li, Csaba Szepesvári, Dale Schuurmans

We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal is to estimate a confidence interval on a target policy's value, given only access to a static experience dataset collected by unknown behavior policies. Starting from a function space embedding of the linear program formulation of the $Q$-function, we obtain an optimization problem with generalized estimating equation constraints. By applying the generalized empirical likelihood method to the resulting Lagrangian, we propose CoinDICE, a novel and efficient algorithm for computing confidence intervals. Theoretically, we prove the obtained confidence intervals are valid, in both asymptotic and finite-sample regimes. Empirically, we show in a variety of benchmarks that the confidence interval estimates are tighter and more accurate than existing methods.

📄 PDF Abstract BibTeX arXiv:2010.11652

Code (0)

등록된 구현이 없습니다.

Tasks

Off-policy evaluationReinforcement Learning (RL)valid

Similar Papers 제목 키워드 기반

Accountable Off-Policy Evaluation via a Kernelized Bellman Statistics

2020-01-01 · ICML 2020 1 · Yihao Feng, Tongzheng Ren, Ziyang Tang, Qiang Liu

Off-policy evaluation plays an important role in modern reinforcement learning. However, most of the existing off-policy evaluation only focus on the value estimation, without providing an accountable confidence interval…

Off-policy evaluation

Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments

2023-02-23 · Vincent Liu, Yash Chandak, Philip Thomas, Martha White

In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but ex…

Multi-Armed BanditsregressionSurvey Samplingvalid

Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation

2020-07-27 · Ilya Kostrikov, Ofir Nachum

In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches. Although straightforward, these technique…

continuous-controlContinuous ControlOff-policy evaluation

Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains

2010-12-01 · NeurIPS 2010 12 · Martha White, Adam White

The reinforcement learning community has explored many approaches to obtain- ing value estimates and models to guide decision making; these approaches, how- ever, do not usually provide a measure of confidence in the est…

Decision Makingparameter estimationreinforcement-learningReinforcement Learning+1

Empirical Likelihood for Contextual Bandits

2019-06-07 · NeurIPS 2020 12 · Nikos Karampatziakis, John Langford, Paul Mineiro

We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator a…

Multi-Armed Bandits