{"total":34,"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":"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":"2410.02226","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","created":"2024-10-03","cited_by_count":8,"area":"deeprl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","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":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2410.05655","title":"Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning","created":"2024-10-08","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","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":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","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":"2411.14341","title":"Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect","created":"2024-11-21","cited_by_count":4,"area":"deeprl"},{"id":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4,"area":"deeprl"},{"id":"2507.20068","title":"PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data","created":"2025-07-26","cited_by_count":4,"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":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2411.07700","title":"Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning","created":"2024-11-12","cited_by_count":2,"area":"deeprl"},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2602.10305","title":"Confounding Robust Continuous Control via Automatic Reward Shaping","created":"2026-02-10","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":"2601.03015","title":"In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior","created":"2026-01-06","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":"2603.28681","title":"Functional Natural Policy Gradients","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2608.12973","title":"Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning","created":"2026-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2509.09208","title":"Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning","created":"2025-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2509.11367","title":"Detecting Model Drifts in Non-Stationary Environment Using Edit Operation Measures","created":"2025-09-14","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":"2602.05379","title":"Variance Reduction Based Experience Replay for Policy Optimization","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2605.24759","title":"A Contractive Feedback Semantics for Reinforcement Learning","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.08925","title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions","created":"2026-07-09","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"},{"id":"2609.39911","title":"Patient-Centered Treatment Planning for Chronic Multimorbidity: A Hierarchical Reinforcement Learning Framework for Preference Modeling","created":"2026-09-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}