SOTAVerified

Off-policy evaluation

Off-policy Evaluation (OPE), or offline evaluation in general, evaluates the performance of hypothetical policies leveraging only offline log data. It is particularly useful in applications where the online interaction involves high stakes and expensive setting such as precision medicine and recommender systems.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–210 of 265 papers

TitleStatusHype
Deep Jump Q-Evaluation for Offline Policy Evaluation in Continuous Action Space—0
Accountable Off-Policy Evaluation With Kernel Bellman Statistics—0
Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation—0
Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders—0
Off-Policy Evaluation via the Regularized Lagrangian—0
Off-Policy Exploitability-Evaluation in Two-Player Zero-Sum Markov Games—0
Strictly Batch Imitation Learning by Energy-based Distribution MatchingCode0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
A maximum-entropy approach to off-policy evaluation in average-reward MDPs—0
Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales—0
Show:102550
← PrevPage 21 of 27Next →

No leaderboard results yet.