{"total":21,"rows":[{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2205.11140","title":"Human-in-the-loop: Provably Efficient Preference-based Reinforcement Learning with General Function Approximation","created":"2022-05-23","cited_by_count":81,"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":"2105.14363","title":"On the Theory of Reinforcement Learning with Once-per-Episode Feedback","created":"2021-05-29","cited_by_count":32,"area":null},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30,"area":null},{"id":"2110.08847","title":"Provable RL with Exogenous Distractors via Multistep Inverse Dynamics","created":"2021-10-17","cited_by_count":28,"area":null},{"id":"2310.03301","title":"Learning Energy Decompositions for Partial Inference of GFlowNets","created":"2023-10-05","cited_by_count":24,"area":null},{"id":"2412.11120","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2102.03400","title":"Confidence-Budget Matching for Sequential Budgeted Learning","created":"2021-02-05","cited_by_count":12,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2102.00490","title":"Online Markov Decision Processes with Aggregate Bandit Feedback","created":"2021-01-31","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":"2409.12798","title":"Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2306.03293","title":"Towards Fairness in Personalized Ads Using Impression Variance Aware Reinforcement Learning","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2312.10642","title":"Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward","created":"2023-12-17","cited_by_count":2,"area":null},{"id":"2510.17103","title":"Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2210.09255","title":"A Unified Algorithm for Stochastic Path Problems","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2412.14779","title":"Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2503.13194","title":"A representational framework for learning and encoding structurally enriched trajectories in complex agent environments","created":"2025-03-17","cited_by_count":0,"area":null}],"next_cursor":null}