{"total":103,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66,"area":"offlinerl"},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64,"area":"wm"},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2110.00188","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","created":"2021-10-01","cited_by_count":47,"area":"offlinerl"},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26,"area":null},{"id":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26,"area":null},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2010.08891","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","created":"2020-10-18","cited_by_count":16,"area":"offlinerl"},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2504.08161","title":"Rethinking the Foundations for Continual Reinforcement Learning","created":"2025-04-10","cited_by_count":15,"area":"deeprl"},{"id":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"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":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2106.11779","title":"Emphatic Algorithms for Deep Reinforcement Learning","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2306.00321","title":"Improving Offline RL by Blending Heuristics","created":"2023-06-01","cited_by_count":10,"area":"offlinerl"},{"id":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2408.08706","title":"Efficient Multi-Policy Evaluation for Reinforcement Learning","created":"2024-08-16","cited_by_count":9,"area":"deeprl"},{"id":"2410.02226","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","created":"2024-10-03","cited_by_count":8,"area":"deeprl"},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2511.03618","title":"Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach","created":"2025-11-05","cited_by_count":7,"area":"deeprl"},{"id":"2106.06508","title":"Preferential Temporal Difference Learning","created":"2021-06-11","cited_by_count":6,"area":null},{"id":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2410.05655","title":"Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning","created":"2024-10-08","cited_by_count":6,"area":"deeprl"},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5,"area":"offlinerl"},{"id":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"area":"offlinerl"},{"id":"2409.12135","title":"Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features","created":"2024-09-18","cited_by_count":5,"area":"deeprl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2501.15034","title":"Divergence-Augmented Policy Optimization","created":"2025-01-25","cited_by_count":4,"area":"deeprl"},{"id":"2109.05110","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms in the Four Rooms Environment","created":"2021-09-10","cited_by_count":3,"area":null},{"id":"2201.06468","title":"Chaining Value Functions for Off-Policy Learning","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2208.00755","title":"Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2208.03247","title":"An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2305.18491","title":"Towards a Better Understanding of Representation Dynamics under TD-learning","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2102.09745","title":"Decentralized Deterministic Multi-Agent Reinforcement Learning","created":"2021-02-19","cited_by_count":2,"area":null},{"id":"2106.00922","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task","created":"2021-06-02","cited_by_count":2,"area":null},{"id":"2110.06906","title":"PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2201.09653","title":"The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning","created":"2022-01-24","cited_by_count":2,"area":null},{"id":"2305.15621","title":"Matrix Estimation for Offline Reinforcement Learning with Low-Rank Structure","created":"2023-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"2307.15892","title":"A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using $L$-$\\lambda$ Smoothness","created":"2023-07-29","cited_by_count":2,"area":null},{"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":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2102.07889","title":"Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport","created":"2021-02-15","cited_by_count":1,"area":null},{"id":"2107.02711","title":"A Unified Off-Policy Evaluation Approach for General Value Function","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2110.10017","title":"Neural Network Compatible Off-Policy Natural Actor-Critic Algorithm","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2203.10172","title":"Importance Sampling Placement in Off-Policy Temporal-Difference Methods","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2206.08111","title":"On Private Online Convex Optimization: Optimal Algorithms in $\\ell_p$-Geometry and High Dimensional Contextual Bandits","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.04624","title":"Gradient Descent Temporal Difference-difference Learning","created":"2022-09-10","cited_by_count":1,"area":null},{"id":"2306.09800","title":"$\\pi2\\text{vec}$: Policy Representations with Successor Features","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2311.14885","title":"Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning","created":"2023-11-25","cited_by_count":1,"area":"offlinerl"},{"id":"2404.10393","title":"Offline Trajectory Optimization for Offline Reinforcement Learning","created":"2024-04-16","cited_by_count":1,"area":"offlinerl"},{"id":"2404.15518","title":"An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2602.12375","title":"Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2603.21663","title":"TAMTRL: Teacher-Aligned Reward Reshaping for Multi-Turn Reinforcement Learning in Long-Context Compression","created":"2026-03-23","cited_by_count":1,"area":"alignment"},{"id":"2102.10527","title":"Delayed Rewards Calibration via Reward Empirical Sufficiency","created":"2021-02-21","cited_by_count":0,"area":null},{"id":"2201.05034","title":"Criticality-Based Varying Step-Number Algorithm for Reinforcement Learning","created":"2022-01-13","cited_by_count":0,"area":null},{"id":"2210.12282","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2310.08091","title":"Discerning Temporal Difference Learning","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2406.07541","title":"CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2407.04974","title":"Multi-agent Off-policy Actor-Critic Reinforcement Learning for Partially Observable Environments","created":"2024-07-06","cited_by_count":0,"area":null},{"id":"2509.22964","title":"Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.25514","title":"Convergence of off-policy TD(0) with linear function approximation for reversible Markov chains","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2605.04100","title":"Regularized Centered Emphatic Temporal Difference Learning","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.11880","title":"Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.28855","title":"Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":"100"}