{"total":53,"rows":[{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2106.06630","title":"Corruption-Robust Offline Reinforcement Learning","created":"2021-06-11","cited_by_count":51,"area":"offlinerl"},{"id":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51,"area":null},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2110.03580","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","created":"2021-10-07","cited_by_count":45,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2106.02847","title":"Navigating to the Best Policy in Markov Decision Processes","created":"2021-06-05","cited_by_count":29,"area":null},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29,"area":null},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2207.14800","title":"Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning","created":"2022-07-29","cited_by_count":26,"area":null},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23,"area":null},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2209.15382","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17,"area":null},{"id":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","cited_by_count":17,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","cited_by_count":14,"area":null},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"area":null},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2310.11550","title":"Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback","created":"2023-10-17","cited_by_count":13,"area":null},{"id":"2301.12579","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","created":"2023-01-29","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":"2306.12356","title":"Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2505.15694","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","created":"2025-05-21","cited_by_count":8,"area":"alignment"},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2306.09554","title":"Low-Switching Policy Gradient with Exploration via Online Sensitivity Sampling","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2307.00405","title":"Provably Efficient UCB-type Algorithms For Learning Predictive State Representations","created":"2023-07-01","cited_by_count":6,"area":null},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2402.02700","title":"Sample Complexity Characterization for Linear Contextual MDPs","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2512.23816","title":"Improved Bounds for Private and Robust Alignment","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2311.07876","title":"Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2406.11640","title":"Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions","created":"2024-06-17","cited_by_count":4,"area":"deeprl"},{"id":"2502.15968","title":"Enhancing PPO with Trajectory-Aware Hybrid Policies","created":"2025-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2308.05471","title":"Provably Efficient Algorithm for Nonstationary Low-Rank MDPs","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2408.12307","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","created":"2024-08-22","cited_by_count":2,"area":"offlinerl"},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2510.18713","title":"Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options","created":"2025-10-21","cited_by_count":2,"area":"alignment"},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2407.05704","title":"Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2512.24768","title":"Sparse Offline Reinforcement Learning with Corruption Robustness","created":"2025-12-31","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}