{"total":22,"rows":[{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101,"area":null},{"id":"2307.04345","title":"Continual Learning as Computationally Constrained Reinforcement Learning","created":"2023-07-10","cited_by_count":37,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2505.10361","title":"Plasticity as the Mirror of Empowerment","created":"2025-05-15","cited_by_count":12,"area":null},{"id":"2211.01595","title":"Reinforcement Learning in Non-Markovian Environments","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2311.00123","title":"Q-Learning for Stochastic Control under General Information Structures and Non-Markovian Environments","created":"2023-10-31","cited_by_count":7,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2306.05991","title":"Approximate information state based convergence analysis of recurrent Q-learning","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2408.02930","title":"The Need for a Big World Simulator: A Scientific Challenge for Continual Learning","created":"2024-08-06","cited_by_count":5,"area":null},{"id":"2210.16872","title":"Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction","created":"2022-10-30","cited_by_count":4,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2601.14711","title":"DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs","created":"2026-01-21","cited_by_count":4,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2511.04666","title":"Forgetting is Everywhere","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2512.10937","title":"Agent policies from higher-order causal functions","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2604.08756","title":"Artifacts as Memory Beyond the Agent Boundary","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2609.12486","title":"Adaptive Agent Design","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}