{"total":30,"rows":[{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2403.13765","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","created":"2024-03-20","cited_by_count":10,"area":"deeprl"},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","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":"2505.20268","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","created":"2025-05-26","cited_by_count":7,"area":"deeprl"},{"id":"2404.03774","title":"Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning","created":"2024-04-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.07253","title":"Hybrid Reinforcement Learning from Offline Observation Alone","created":"2024-06-11","cited_by_count":5,"area":"deeprl"},{"id":"2407.10454","title":"Deflated Dynamics Value Iteration","created":"2024-07-15","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":"2501.06366","title":"Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing","created":"2025-01-10","cited_by_count":5,"area":"deeprl"},{"id":"2401.12216","title":"Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning","created":"2024-01-22","cited_by_count":4,"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":"2407.08803","title":"PID Accelerated Temporal Difference Algorithms","created":"2024-07-11","cited_by_count":2,"area":"deeprl"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2403.10946","title":"The Fallacy of Minimizing Cumulative Regret in the Sequential Task Setting","created":"2024-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2502.07715","title":"Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"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":"2507.04406","title":"Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning","created":"2025-07-06","cited_by_count":1,"area":"deeprl"},{"id":"2510.00885","title":"Rectifying Regression in Reinforcement Learning","created":"2025-10-01","cited_by_count":1,"area":"deeprl"},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.20220","title":"Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning","created":"2025-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.00716","title":"Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\\pi}$ Realizability for Deterministic Dynamics","created":"2026-02-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.06373","title":"Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $\\tau$-Mixing","created":"2026-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2608.08743","title":"A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning","created":"2026-08-09","cited_by_count":0,"area":"deeprl"},{"id":"2609.30391","title":"From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2609.35466","title":"An analysis of Mirror-Descent Soft Actor-Critic","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.04754","title":"FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies","created":"2026-10-03","cited_by_count":0,"area":"deeprl"},{"id":"2610.12135","title":"Q-Shaped Options for Hierarchical Reinforcement Learning","created":"2026-10-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}