{"total":87,"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":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2303.02783","title":"Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning","created":"2023-03-05","cited_by_count":44,"area":null},{"id":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36,"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":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29,"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":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22,"area":null},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"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":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"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":"2301.11721","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","created":"2023-01-27","cited_by_count":16,"area":null},{"id":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16,"area":"offlinerl"},{"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":"2406.15788","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","created":"2024-06-22","cited_by_count":15,"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":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2310.18434","title":"Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage","created":"2023-10-27","cited_by_count":12,"area":"offlinerl"},{"id":"2302.01248","title":"Robust Markov Decision Processes without Model Estimation","created":"2023-02-02","cited_by_count":11,"area":null},{"id":"2402.05876","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","created":"2024-02-08","cited_by_count":11,"area":"offlinerl"},{"id":"2406.17096","title":"Model-Free Robust Reinforcement Learning with Sample Complexity Analysis","created":"2024-06-24","cited_by_count":9,"area":"deeprl"},{"id":"2506.08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":9,"area":"offlinerl"},{"id":"2306.05859","title":"Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"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":"2503.20613","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","created":"2025-03-26","cited_by_count":8,"area":"deeprl"},{"id":"2407.04285","title":"Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling","created":"2024-07-05","cited_by_count":7,"area":"offlinerl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2503.20844","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","created":"2025-03-26","cited_by_count":7,"area":"deeprl"},{"id":"2502.02844","title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2512.02486","title":"Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts","created":"2025-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","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":"2503.08934","title":"Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model","created":"2025-03-11","cited_by_count":5,"area":"deeprl"},{"id":"2505.18044","title":"Linear Mixture Distributionally Robust Markov Decision Processes","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2309.08925","title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning","created":"2023-09-16","cited_by_count":4,"area":"offlinerl"},{"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":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"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":"2306.08364","title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","created":"2023-06-14","cited_by_count":3,"area":"offlinerl"},{"id":"2407.10967","title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning","created":"2024-07-15","cited_by_count":3,"area":"offlinerl"},{"id":"2505.12462","title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis","created":"2025-05-18","cited_by_count":3,"area":"deeprl"},{"id":"2505.23003","title":"Hybrid Cross-domain Robust Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","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":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2503.12283","title":"Towards Optimal Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2505.13709","title":"Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":2,"area":"wm"},{"id":"2505.23871","title":"ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning","created":"2025-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2512.18957","title":"Online Robust Reinforcement Learning with General Function Approximation","created":"2025-12-22","cited_by_count":2,"area":"deeprl"},{"id":"2605.29032","title":"Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning","created":"2026-05-27","cited_by_count":2,"area":"wm"},{"id":"2310.02459","title":"Distributionally Safe Reinforcement Learning under Model Uncertainty: A Single-Level Approach by Differentiable Convex Programming","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2406.04081","title":"Bootstrapping Expectiles in Reinforcement Learning","created":"2024-06-06","cited_by_count":1,"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":"2503.20660","title":"DR-PETS: Learning-Based Control With Planning in Adversarial Environments","created":"2025-03-26","cited_by_count":1,"area":null},{"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":"2506.21129","title":"Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2509.24047","title":"Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2511.07831","title":"Distributionally Robust Online Markov Game with Linear Function Approximation","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"id":"2512.00030","title":"Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning","created":"2025-11-08","cited_by_count":1,"area":"deeprl"},{"id":"2512.03847","title":"DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2603.23738","title":"BXRL: Behavior-Explainable Reinforcement Learning","created":"2026-03-24","cited_by_count":1,"area":"deeprl"},{"id":"2604.07072","title":"Epistemic Robust Offline Reinforcement Learning","created":"2026-04-08","cited_by_count":1,"area":"offlinerl"},{"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":"2505.04193","title":"Trajectory Entropy Reinforcement Learning for Robust Robot Motor Skill Learning","created":"2025-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2505.16734","title":"Maximum Total Correlation Reinforcement Learning","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2506.13207","title":"Research on Optimal Control Problem Based on Reinforcement Learning under Knightian Uncertainty","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2510.01721","title":"Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation","created":"2025-10-02","cited_by_count":0,"area":"deeprl"},{"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":"2605.08417","title":"Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2606.03521","title":"Post-Hoc Robustness for Model-Based Reinforcement Learning","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2606.22579","title":"Stationary Robust Mean-Field Games under Model Mismatches","created":"2026-06-21","cited_by_count":0,"area":"deeprl"},{"id":"2609.28792","title":"Vector Bellman Theory for Multichain Robust Average-Reward Markov Decision Processes","created":"2026-09-23","cited_by_count":0,"area":null},{"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}