{"total":149,"rows":[{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2109.06332","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"area":null},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34,"area":null},{"id":"2206.11889","title":"Provably Efficient Model-Free Constrained RL with Linear Function Approximation","created":"2022-06-23","cited_by_count":31,"area":null},{"id":"2107.05216","title":"A Simple Reward-free Approach to Constrained Reinforcement Learning","created":"2021-07-12","cited_by_count":30,"area":null},{"id":"2211.07484","title":"Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression","created":"2022-11-14","cited_by_count":30,"area":null},{"id":"2202.00150","title":"Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints","created":"2022-01-31","cited_by_count":29,"area":null},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"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":"2304.09362","title":"Long-Term Fairness with Unknown Dynamics","created":"2023-04-19","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":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23,"area":null},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2102.03192","title":"Provably Efficient Algorithms for Multi-Objective Competitive RL","created":"2021-02-05","cited_by_count":22,"area":null},{"id":"2303.05733","title":"Provably Efficient Model-Free Algorithms for Non-stationary CMDPs","created":"2023-03-10","cited_by_count":21,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2306.01854","title":"Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space","created":"2023-06-02","cited_by_count":18,"area":null},{"id":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2203.09251","title":"Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs","created":"2022-03-17","cited_by_count":17,"area":null},{"id":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2403.03672","title":"Learning Adversarial MDPs with Stochastic Hard Constraints","created":"2024-03-06","cited_by_count":16,"area":"deeprl"},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","cited_by_count":15,"area":null},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2406.15788","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","created":"2024-06-22","cited_by_count":15,"area":"deeprl"},{"id":"2209.13694","title":"Safe Linear Bandits over Unknown Polytopes","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2306.00212","title":"Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2206.01588","title":"Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games","created":"2022-06-03","cited_by_count":12,"area":null},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2410.02275","title":"Optimal Strong Regret and Violation in Constrained MDPs via Policy Optimization","created":"2024-10-03","cited_by_count":12,"area":"deeprl"},{"id":"2509.00125","title":"Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning","created":"2025-08-29","cited_by_count":12,"area":"lr"},{"id":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2405.10624","title":"Sample-Efficient Constrained Reinforcement Learning with General Parameterization","created":"2024-05-17","cited_by_count":11,"area":"deeprl"},{"id":"2201.11965","title":"Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2206.14057","title":"Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-free RL","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2312.10303","title":"Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2408.16286","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","created":"2024-08-29","cited_by_count":10,"area":"deeprl"},{"id":"2411.02957","title":"Embedding Safety into RL: A New Take on Trust Region Methods","created":"2024-11-05","cited_by_count":10,"area":"deeprl"},{"id":"2106.11692","title":"A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning","created":"2021-06-22","cited_by_count":9,"area":null},{"id":"2304.14326","title":"A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints","created":"2023-04-27","cited_by_count":9,"area":null},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2402.02042","title":"Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm","created":"2024-02-03","cited_by_count":9,"area":"deeprl"},{"id":"2306.00324","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2402.03077","title":"Markov Persuasion Processes: Learning to Persuade from Scratch","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2404.16879","title":"Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey","created":"2024-04-22","cited_by_count":8,"area":"deeprl"},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"id":"2505.15138","title":"Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm","created":"2025-05-21","cited_by_count":8,"area":"deeprl"},{"id":"2306.07001","title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2306.07749","title":"Provably Learning Nash Policies in Constrained Markov Potential Games","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2312.14470","title":"Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2502.18655","title":"Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces","created":"2025-02-25","cited_by_count":7,"area":"deeprl"},{"id":"2311.05511","title":"Anytime-Constrained Reinforcement Learning","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2401.17780","title":"A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees","created":"2024-01-31","cited_by_count":6,"area":"deeprl"},{"id":"2502.10138","title":"Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation","created":"2025-02-14","cited_by_count":6,"area":"deeprl"},{"id":"2505.19238","title":"Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees","created":"2025-05-25","cited_by_count":6,"area":"deeprl"},{"id":"2505.21841","title":"An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints","created":"2025-05-28","cited_by_count":6,"area":"deeprl"},{"id":"2108.03952","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","created":"2021-08-09","cited_by_count":5,"area":null},{"id":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2302.01517","title":"Pseudonorm Approachability and Applications to Regret Minimization","created":"2023-02-03","cited_by_count":5,"area":null},{"id":"2302.02426","title":"Online Nonstochastic Control with Adversarial and Static Constraints","created":"2023-02-05","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2403.15928","title":"Safe Reinforcement Learning for Constrained Markov Decision Processes with Stochastic Stopping Time","created":"2024-03-23","cited_by_count":5,"area":"deeprl"},{"id":"2405.14372","title":"Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints","created":"2024-05-23","cited_by_count":5,"area":"deeprl"},{"id":"2406.18529","title":"Confident Natural Policy Gradient for Local Planning in $q_\\pi$-realizable Constrained MDPs","created":"2024-06-26","cited_by_count":5,"area":"deeprl"},{"id":"2506.13244","title":"No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2510.20235","title":"Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach","created":"2025-10-23","cited_by_count":5,"area":"deeprl"},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2508.05441","title":"Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2509.16586","title":"Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2106.06680","title":"Markov Decision Processes with Long-Term Average Constraints","created":"2021-06-12","cited_by_count":3,"area":null},{"id":"2301.02389","title":"Provable Reset-free Reinforcement Learning by No-Regret Reduction","created":"2023-01-06","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2409.15128","title":"The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes","created":"2024-09-23","cited_by_count":3,"area":null},{"id":"2105.09295","title":"Online Selection of Diverse Committees","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2106.04944","title":"Non-Parametric Stochastic Sequential Assignment With Random Arrival Times","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2402.10810","title":"Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning","created":"2024-02-16","cited_by_count":2,"area":"deeprl"},{"id":"2405.19017","title":"Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling","created":"2024-05-29","cited_by_count":2,"area":"deeprl"},{"id":"2502.11673","title":"Best of Both Worlds: Regret Minimization versus Minimax Play","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.06751","title":"Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints","created":"2025-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2505.20010","title":"Data-Dependent Regret Bounds for Constrained MABs","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.04291","title":"A Lyapunov Drift-Plus-Penalty Method Tailored for Reinforcement Learning with Queue Stability","created":"2025-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2602.14580","title":"Replicable Constrained Bandits","created":"2026-02-16","cited_by_count":2,"area":null}],"next_cursor":"100"}