{"total":21,"rows":[{"id":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2510.22512","title":"Transitive RL: Value Learning via Divide and Conquer","created":"2025-10-26","cited_by_count":12,"area":"deeprl"},{"id":"2402.08201","title":"Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap","created":"2024-02-13","cited_by_count":8,"area":"deeprl"},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8,"area":"deeprl"},{"id":"2403.00675","title":"Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate","created":"2024-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2412.05783","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","created":"2024-12-08","cited_by_count":5,"area":"deeprl"},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2501.15034","title":"Divergence-Augmented Policy Optimization","created":"2025-01-25","cited_by_count":4,"area":"deeprl"},{"id":"2405.18792","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","created":"2024-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2410.02172","title":"Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation","created":"2024-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2402.12034","title":"When Do Off-Policy and On-Policy Policy Gradient Methods Align?","created":"2024-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2503.02125","title":"Average-DICE: Stationary Distribution Correction by Regression","created":"2025-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2608.24146","title":"Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation","created":"2026-08-25","cited_by_count":2,"area":"deeprl"},{"id":"2505.22492","title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","created":"2025-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2602.01853","title":"Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"deeprl"},{"id":"2403.01605","title":"Towards Provable Log Density Policy Gradient","created":"2024-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2509.19464","title":"Evaluation-Aware Reinforcement Learning","created":"2025-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2609.13044","title":"Robust Policy Optimization via Adversarial Importance Sampling","created":"2026-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2609.23374","title":"The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions","created":"2026-09-20","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}