policy evaluation

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation COLT 2022 Policy Evaluation and Temporal-Difference Learning in Continuous Time and Space: A Martingale Approach JMLR 2022 ReVar: Strengthening policy evaluation via reduced variance sampling UAI 2022 Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning NeurIPS 2022 Safe Exploration for Efficient Policy Evaluation and Comparison ICML 2022 Sample Complexity of Policy-Based Methods under Off-Policy Sampling and Linear Function Approximation AISTATS 2022 Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters ICML 2022 Batch Reinforcement Learning Through Continuation Method ICLR 2021 BCORLE(λ): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market NeurIPS 2021 Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators NeurIPS 2021 Instabilities of Offline RL with Pre-Trained Neural Representation ICML 2021 Loop Estimator for Discounted Values in Markov Reward Processes AAAI 2021 Nearly Horizon-Free Offline Reinforcement Learning NeurIPS 2021 Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation NeurIPS 2021 Post-Contextual-Bandit Inference NeurIPS 2021 Preferential Temporal Difference Learning ICML 2021 What are the Statistical Limits of Offline RL with Linear Function Approximation? ICLR 2021 You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL CoRL 2021 A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound AAAI 2020 Attentive Experience Replay AAAI 2020 Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits ICML 2020 Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise COLT 2020 MOReL: Model-Based Offline Reinforcement Learning NeurIPS 2020 Reanalysis of Variance Reduced Temporal Difference Learning ICLR 2020 SVRG for Policy Evaluation with Fewer Gradient Evaluations IJCAI 2020