{"total":38,"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":"2111.13485","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2212.10420","title":"Settling the Reward Hypothesis","created":"2022-12-20","cited_by_count":33,"area":null},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"area":null},{"id":"2307.13372","title":"Submodular Reinforcement Learning","created":"2023-07-25","cited_by_count":23,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19,"area":null},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2302.10030","title":"Safe Deep Reinforcement Learning by Verifying Task-Level Properties","created":"2023-02-20","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":"2206.13637","title":"Utility Theory for Sequential Decision Making","created":"2022-06-27","cited_by_count":8,"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":"2205.15400","title":"Designing Rewards for Fast Learning","created":"2022-05-30","cited_by_count":7,"area":null},{"id":"2206.00257","title":"CoNSoLe: Convex Neural Symbolic Learning","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2211.10861","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","created":"2022-11-20","cited_by_count":4,"area":null},{"id":"2307.12184","title":"On the Expressivity of Multidimensional Markov Reward","created":"2023-07-22","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":"2305.16621","title":"A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2312.04736","title":"Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2402.07051","title":"$L^*LM$: Learning Automata from Examples using Natural Language Oracles","created":"2024-02-10","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":"2112.10807","title":"Demonstration Informed Specification Search","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2303.09027","title":"Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2311.05084","title":"Signal Temporal Logic-Guided Apprenticeship Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2505.17024","title":"An Affective-Taxis Hypothesis for Alignment and Interpretability","created":"2025-05-03","cited_by_count":1,"area":null},{"id":"2506.13803","title":"Causality in the human niche: lessons for machine learning","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2602.15407","title":"Fairness over Equality: Correcting Social Incentives in Asymmetric Sequential Social Dilemmas","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2202.03192","title":"Reward is not enough: can we liberate AI from the reinforcement learning paradigm?","created":"2022-02-03","cited_by_count":0,"area":null},{"id":"2207.08258","title":"Minimum Description Length Control","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2212.03733","title":"Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior","created":"2022-12-07","cited_by_count":0,"area":null},{"id":"2411.10601","title":"Learning Quantitative Automata Modulo Theories","created":"2024-11-15","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}