{"total":71,"rows":[{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203,"area":"alignment"},{"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":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"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":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"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":"2210.15629","title":"Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks","created":"2022-10-27","cited_by_count":20,"area":"diffusion"},{"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":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"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":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2410.12175","title":"Reinforcement Learning with LTL and $\\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards","created":"2024-10-16","cited_by_count":14,"area":"deeprl"},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2404.11578","title":"LTL-Constrained Policy Optimization with Cycle Experience Replay","created":"2024-04-17","cited_by_count":11,"area":"deeprl"},{"id":"2302.13493","title":"The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning","created":"2023-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9,"area":"offlinerl"},{"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":"2401.14811","title":"On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks","created":"2024-01-26","cited_by_count":9,"area":"deeprl"},{"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":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"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":"2408.09495","title":"Directed Exploration in Reinforcement Learning from Linear Temporal Logic","created":"2024-08-18","cited_by_count":7,"area":"deeprl"},{"id":"2409.15922","title":"The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards","created":"2024-09-24","cited_by_count":7,"area":"mllm"},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2306.15156","title":"Learning non-Markovian Decision-Making from State-only Sequences","created":"2023-06-27","cited_by_count":6,"area":"offlinerl"},{"id":"2503.16799","title":"Causally Aligned Curriculum Learning","created":"2025-03-21","cited_by_count":6,"area":"deeprl"},{"id":"2211.02667","title":"Deconfounding Imitation Learning with Variational Inference","created":"2022-11-04","cited_by_count":5,"area":"offlinerl"},{"id":"2401.11325","title":"Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov","created":"2024-01-20","cited_by_count":5,"area":"deeprl"},{"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":"2509.10423","title":"Mutual Information Tracks Policy Coherence in Reinforcement Learning","created":"2025-09-12","cited_by_count":4,"area":"deeprl"},{"id":"2605.15960","title":"Imperfect World Models are Exploitable","created":"2026-05-15","cited_by_count":4,"area":"wm"},{"id":"2204.05909","title":"Learning Performance Graphs from Demonstrations via Task-Based Evaluations","created":"2022-04-12","cited_by_count":3,"area":"offlinerl"},{"id":"2311.01990","title":"Conditions on Preference Relations that Guarantee the Existence of Optimal Policies","created":"2023-11-03","cited_by_count":3,"area":"alignment"},{"id":"2410.23680","title":"Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment","created":"2024-10-31","cited_by_count":3,"area":"offlinerl"},{"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":"2302.08734","title":"A State Augmentation based approach to Reinforcement Learning from Human Preferences","created":"2023-02-17","cited_by_count":2,"area":"alignment"},{"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":"2512.21527","title":"Generative Actor Critic","created":"2025-12-25","cited_by_count":2,"area":"deeprl"},{"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":"2404.08791","title":"Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch","created":"2024-04-12","cited_by_count":1,"area":"alignment"},{"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":"2507.00611","title":"Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics","created":"2025-07-01","cited_by_count":1,"area":"alignment"},{"id":"2508.04282","title":"Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling","created":"2025-08-06","cited_by_count":1,"area":"deeprl"},{"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":"2508.15013","title":"Goals and the Structure of Experience","created":"2025-08-20","cited_by_count":0,"area":"wm"},{"id":"2512.01047","title":"Automating the Refinement of Reinforcement Learning Specifications","created":"2025-11-30","cited_by_count":0,"area":"deeprl"},{"id":"2603.08412","title":"Aligning to Illusions: Choice Blindness in Human and AI Feedback","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2606.19328","title":"UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}