{"total":9,"rows":[{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2311.08290","title":"On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2403.17285","title":"Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments","created":"2024-03-26","cited_by_count":6,"area":null},{"id":"2502.02516","title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2305.04361","title":"Truncating Trajectories in Monte Carlo Reinforcement Learning","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2508.01049","title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2609.38096","title":"Tail-Influence Sampling for CVaR Policy Evaluation","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}