{"total":46,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2207.07150","title":"Making Linear MDPs Practical via Contrastive Representation Learning","created":"2022-07-14","cited_by_count":52,"area":null},{"id":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"area":null},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2106.12764","title":"Density Constrained Reinforcement Learning","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12,"area":null},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2311.12244","title":"Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"area":null},{"id":"2202.07071","title":"A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2304.10613","title":"Debiasing Conditional Stochastic Optimization","created":"2023-04-20","cited_by_count":6,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5,"area":null},{"id":"2408.11084","title":"Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2409.05539","title":"CoBo: Collaborative Learning via Bilevel Optimization","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2504.16667","title":"Representation Learning via Non-Contrastive Mutual Information","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2109.11867","title":"The $f$-Divergence Reinforcement Learning Framework","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2501.04426","title":"Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2506.08062","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","created":"2025-06-09","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":"2103.09756","title":"Near Optimal Policy Optimization via REPS","created":"2021-03-17","cited_by_count":1,"area":null},{"id":"2201.00236","title":"Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning","created":"2022-01-01","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":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2303.06654","title":"Twice Regularized Markov Decision Processes: The Equivalence between Robustness and Regularization","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.08644","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2509.19800","title":"Analysis of approximate linear programming solution to Markov decision problem with log barrier function","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2110.12081","title":"Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2203.16177","title":"Marginalized Operators for Off-policy Reinforcement Learning","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2210.00770","title":"Accelerate Reinforcement Learning with PID Controllers in the Pendulum Simulations","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2301.03183","title":"Minimax Weight Learning for Absorbing MDPs","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2509.15103","title":"Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2601.20154","title":"Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning","created":"2026-01-28","cited_by_count":0,"area":null}],"next_cursor":null}