{"total":51,"rows":[{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"area":null},{"id":"2307.08875","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","created":"2023-07-17","cited_by_count":36,"area":null},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25,"area":null},{"id":"2402.15399","title":"Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation","created":"2024-02-23","cited_by_count":25,"area":"deeprl"},{"id":"2404.18909","title":"Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty","created":"2024-04-29","cited_by_count":25,"area":null},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2311.09018","title":"On the Foundation of Distributionally Robust Reinforcement Learning","created":"2023-11-15","cited_by_count":18,"area":null},{"id":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2309.02236","title":"Distributionally Robust Model-based Reinforcement Learning with Large State Spaces","created":"2023-09-05","cited_by_count":17,"area":null},{"id":"2305.19004","title":"Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets","created":"2023-05-30","cited_by_count":16,"area":null},{"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":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14,"area":"offlinerl"},{"id":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","cited_by_count":8,"area":"offlinerl"},{"id":"2411.18612","title":"Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization","created":"2024-11-27","cited_by_count":8,"area":"offlinerl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2406.08847","title":"Roping in Uncertainty: Robustness and Regularization in Markov Games","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2505.18044","title":"Linear Mixture Distributionally Robust Markov Decision Processes","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2405.05468","title":"Model-Free Robust $\\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data","created":"2024-05-08","cited_by_count":4,"area":"deeprl"},{"id":"2406.14156","title":"Tractable Equilibrium Computation in Markov Games through Risk Aversion","created":"2024-06-20","cited_by_count":4,"area":"deeprl"},{"id":"2502.06777","title":"Learning an Optimal Assortment Policy under Observational Data","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2508.17448","title":"Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality","created":"2025-08-24","cited_by_count":4,"area":"deeprl"},{"id":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2310.19861","title":"Posterior Sampling for Competitive RL: Function Approximation and Partial Observation","created":"2023-10-30","cited_by_count":3,"area":null},{"id":"2505.23003","title":"Hybrid Cross-domain Robust Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2509.24748","title":"Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption","created":"2025-09-29","cited_by_count":3,"area":"offlinerl"},{"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":"2512.18957","title":"Online Robust Reinforcement Learning with General Function Approximation","created":"2025-12-22","cited_by_count":2,"area":"deeprl"},{"id":"2604.10974","title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","created":"2026-04-13","cited_by_count":2,"area":"deeprl"},{"id":"2412.18781","title":"Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations","created":"2024-12-25","cited_by_count":1,"area":"offlinerl"},{"id":"2505.12202","title":"Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learning","created":"2025-05-18","cited_by_count":1,"area":"deeprl"},{"id":"2509.14077","title":"Online Bayesian Risk-Averse Reinforcement Learning","created":"2025-09-17","cited_by_count":1,"area":"deeprl"},{"id":"2511.03695","title":"Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL","created":"2025-11-05","cited_by_count":1,"area":"offlinerl"},{"id":"2511.05694","title":"Distributionally Robust Self Paced Curriculum Reinforcement Learning","created":"2025-11-07","cited_by_count":1,"area":"deeprl"},{"id":"2511.07831","title":"Distributionally Robust Online Markov Game with Linear Function Approximation","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"id":"2512.01660","title":"Bayesian Ambiguity Contraction-based Adaptive Robust Markov Decision Processes for Adversarial Surveillance Missions","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2404.08089","title":"Efficient Duple Perturbation Robustness in Low-rank MDPs","created":"2024-04-11","cited_by_count":0,"area":"deeprl"},{"id":"2406.11281","title":"Learning Optimal Distributionally Robust Stochastic Control in Continuous State Spaces","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2411.07514","title":"Robust Offline Reinforcement Learning for Non-Markovian Decision Processes","created":"2024-11-12","cited_by_count":0,"area":"offlinerl"},{"id":"2502.06491","title":"Model-Based Offline Reinforcement Learning with Reliability-Guaranteed Sequence Modeling","created":"2025-02-10","cited_by_count":0,"area":"offlinerl"},{"id":"2510.10260","title":"Robust Exploratory Stopping under Ambiguity in Reinforcement Learning","created":"2025-10-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.19950","title":"Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2602.01825","title":"Learning Sequential Decisions from Multiple Sources via Group-Robust Markov Decision Processes","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.11437","title":"Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2605.03125","title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.24345","title":"Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2606.20356","title":"Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.22579","title":"Stationary Robust Mean-Field Games under Model Mismatches","created":"2026-06-21","cited_by_count":0,"area":"deeprl"},{"id":"2610.02131","title":"Linear Programming Representations and Strongly Polynomial Algorithms for Robust Markov Decision Processes","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}