← Keywords

off-policy evaluation

144 papers

Explore in graph

Also known as

OPE

Co-occurring keywords

reinforcement learning (4122) importance sampling (316) contextual bandit (379) causal inference (1619) markov decision process (788) variance reduction (520) doubly robust estimator (37) offline reinforcement learning (492) confidence interval (145) doubly robust (32)

Papers

Empirical Likelihood for Contextual Bandits NIPS 2020
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning AISTATS 2020
Adaptive Trade-Offs in Off-Policy Learning AISTATS 2020
Doubly robust off-policy evaluation with shrinkage ICML 2020
Off-Policy Evaluation in Partially Observable Environments AAAI 2020
Taylor Expansion Policy Optimization ICML 2020
Adaptive Estimator Selection for Off-Policy Evaluation ICML 2020
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling ICML 2020
Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation ICML 2020
From Importance Sampling to Doubly Robust Policy Gradient ICML 2020
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions ICML 2020
Batch Stationary Distribution Estimation ICML 2020
Minimax Weight and Q-Function Learning for Off-Policy Evaluation ICML 2020
Off-Policy Evaluation via the Regularized Lagrangian NIPS 2020
Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning NIPS 2020
Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation NIPS 2020
Accountable Off-Policy Evaluation With Kernel Bellman Statistics ICML 2020
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation ICML 2020
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling NIPS 2019
Bayesian Counterfactual Risk Minimization ICML 2019
Truly Batch Apprenticeship Learning with Deep Successor Features IJCAI 2019
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models ICML 2019
Importance Sampling Policy Evaluation with an Estimated Behavior Policy ICML 2019
Combining parametric and nonparametric models for off-policy evaluation ICML 2019
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting NIPS 2019