{"total":36,"rows":[{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"area":null},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2106.05110","title":"Self-Paced Context Evaluation for Contextual Reinforcement Learning","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2106.05262","title":"TempoRL: Learning When to Act","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"area":null},{"id":"2102.13176","title":"A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2311.01885","title":"Domain Randomization via Entropy Maximization","created":"2023-11-03","cited_by_count":19,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2207.11126","title":"Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP","created":"2022-07-22","cited_by_count":11,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2303.01464","title":"Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2405.17796","title":"Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2510.09127","title":"Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2210.05355","title":"Multi-User Reinforcement Learning with Low Rank Rewards","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2212.10876","title":"Hyperparameters in Contextual RL are Highly Situational","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2206.00270","title":"Provably Efficient Lifelong Reinforcement Learning with Linear Function Approximation","created":"2022-06-01","cited_by_count":2,"area":null},{"id":"2506.09434","title":"When Is Diversity Rewarded in Cooperative Multi-Agent Learning?","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2510.01620","title":"Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPs","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2602.13706","title":"Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2305.16056","title":"Reinforcement Learning under External Influence: Guarantees, Algorithms, and Sample Complexity","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2307.05834","title":"Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2307.11704","title":"JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2502.10476","title":"Multi-Objective Planning with Contextual Lexicographic Reward Preferences","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.03939","title":"C-IDS: Solving Contextual POMDP via Information-Directed Objective","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.05139","title":"Adaptive Exploration for Latent-State Bandits","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2606.20967","title":"Formalizing Task-Space Complexity for Zero-Shot Generalization","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.20799","title":"Dynamic Context Scheduling: Learning Beyond the Static Universe","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}