{"total":15,"rows":[{"id":"2310.00166","title":"Motif: Intrinsic Motivation from Artificial Intelligence Feedback","created":"2023-09-29","cited_by_count":102,"area":null},{"id":"2307.11046","title":"A Definition of Continual Reinforcement Learning","created":"2023-07-20","cited_by_count":101,"area":null},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2505.10361","title":"Plasticity as the Mirror of Empowerment","created":"2025-05-15","cited_by_count":12,"area":null},{"id":"2503.05996","title":"Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners","created":"2025-03-08","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":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2407.18422","title":"A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2505.12049","title":"Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2507.22255","title":"Agent-centric learning: from external reward maximization to internal knowledge curation","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2602.12963","title":"Calculating Mutual Information between a Reward Maximizer and its Environment","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2406.14476","title":"Learning telic-controllable state representations","created":"2024-06-20","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":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}