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 176–200 of 265 papers

TitleStatusHype
Loss Functions for Discrete Contextual Pricing with Observational Data—0
Marginalized Operators for Off-policy Reinforcement Learning—0
Markovian Interference in Experiments—0
Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation—0
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization—0
Minimax Model Learning—0
Minimax Off-Policy Evaluation for Multi-Armed Bandits—0
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation—0
Minimax Weight and Q-Function Learning for Off-Policy Evaluation—0
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization—0
Counterfactual Mean EmbeddingsCode0
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal ModelsCode0
Cross-Validated Off-Policy EvaluationCode0
Off-Policy Evaluation Using Information Borrowing and Context-Based SwitchingCode0
Minimum Empirical Divergence for Sub-Gaussian Linear BanditsCode0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Batch Stationary Distribution EstimationCode0
Model-Free and Model-Based Policy Evaluation when Causality is UncertainCode0
Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment SettingsCode0
Deeply-Debiased Off-Policy Interval EstimationCode0
Deep Proxy Causal Learning and its Application to Confounded Bandit Policy EvaluationCode0
Control Variates for Slate Off-Policy EvaluationCode0
A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided MarketsCode0
State Relevance for Off-Policy EvaluationCode0
More Robust Doubly Robust Off-policy EvaluationCode0
Show:102550
← PrevPage 8 of 11Next →

No leaderboard results yet.