{"total":193,"rows":[{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790,"area":"wm"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2312.11598","title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","created":"2023-12-18","cited_by_count":70,"area":"diffusion"},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45,"area":null},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42,"area":"diffusion"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2303.14623","title":"Inverse Reinforcement Learning without Reinforcement Learning","created":"2023-03-26","cited_by_count":36,"area":"offlinerl"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2311.02496","title":"LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion","created":"2023-11-04","cited_by_count":33,"area":"offlinerl"},{"id":"2402.08848","title":"Hybrid Inverse Reinforcement Learning","created":"2024-02-13","cited_by_count":32,"area":"offlinerl"},{"id":"2203.00054","title":"LISA: Learning Interpretable Skill Abstractions from Language","created":"2022-02-28","cited_by_count":30,"area":"offlinerl"},{"id":"2303.00599","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","created":"2023-03-01","cited_by_count":29,"area":"offlinerl"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2311.02013","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","created":"2023-11-03","cited_by_count":21,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2207.01166","title":"Target-absent Human Attention","created":"2022-07-04","cited_by_count":20,"area":"offlinerl"},{"id":"2302.04782","title":"CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning","created":"2023-02-09","cited_by_count":20,"area":"offlinerl"},{"id":"2405.16194","title":"Diffusion-Reward Adversarial Imitation Learning","created":"2024-05-25","cited_by_count":20,"area":"diffusion"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2312.06348","title":"DiffAIL: Diffusion Adversarial Imitation Learning","created":"2023-12-11","cited_by_count":18,"area":"diffusion"},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2507.00018","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","created":"2025-06-15","cited_by_count":17,"area":"alignment"},{"id":"2302.00965","title":"Visual Imitation Learning with Patch Rewards","created":"2023-02-02","cited_by_count":16,"area":"offlinerl"},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"id":"2306.06563","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","created":"2023-06-11","cited_by_count":16,"area":"offlinerl"},{"id":"2410.13855","title":"Diffusing States and Matching Scores: A New Framework for Imitation Learning","created":"2024-10-17","cited_by_count":16,"area":"diffusion"},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2303.13512","title":"Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition","created":"2023-03-23","cited_by_count":15,"area":"alignment"},{"id":"2405.02181","title":"Imitation Learning in Discounted Linear MDPs without exploration assumptions","created":"2024-05-03","cited_by_count":15,"area":"offlinerl"},{"id":"2306.05426","title":"SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking","created":"2023-06-08","cited_by_count":13,"area":"offlinerl"},{"id":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2410.05429","title":"Diffusion Imitation from Observation","created":"2024-10-07","cited_by_count":13,"area":"diffusion"},{"id":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2210.01282","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":12,"area":"offlinerl"},{"id":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2305.11290","title":"Massively Scalable Inverse Reinforcement Learning in Google Maps","created":"2023-05-18","cited_by_count":11,"area":"offlinerl"},{"id":"2306.13412","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","created":"2023-06-23","cited_by_count":11,"area":"offlinerl"},{"id":"2402.01886","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","created":"2024-02-02","cited_by_count":11,"area":"offlinerl"},{"id":"2405.13193","title":"Efficient Imitation Learning with Conservative World Models","created":"2024-05-21","cited_by_count":11,"area":"wm"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2209.10187","title":"On the convex formulations of robust Markov decision processes","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2306.14799","title":"On Imitation in Mean-field Games","created":"2023-06-26","cited_by_count":10,"area":"offlinerl"},{"id":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10,"area":"offlinerl"},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10,"area":"deeprl"},{"id":"2411.07007","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","created":"2024-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2303.02073","title":"How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement","created":"2023-03-03","cited_by_count":8,"area":"offlinerl"},{"id":"2305.14608","title":"Inverse Reinforcement Learning with the Average Reward Criterion","created":"2023-05-24","cited_by_count":8,"area":"offlinerl"},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2209.13413","title":"Reinforcement Learning with Non-Exponential Discounting","created":"2022-09-27","cited_by_count":7,"area":null},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2312.10385","title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","created":"2023-12-16","cited_by_count":7,"area":null},{"id":"2402.13147","title":"SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning","created":"2024-02-20","cited_by_count":7,"area":"offlinerl"},{"id":"2410.14081","title":"Reward-free World Models for Online Imitation Learning","created":"2024-10-17","cited_by_count":7,"area":"wm"},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2202.04332","title":"Imitation Learning by State-Only Distribution Matching","created":"2022-02-09","cited_by_count":6,"area":"offlinerl"},{"id":"2402.14174","title":"Blending Data-Driven Priors in Dynamic Games","created":"2024-02-21","cited_by_count":6,"area":null},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2406.01793","title":"Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning","created":"2024-06-03","cited_by_count":6,"area":"offlinerl"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2501.12633","title":"Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors","created":"2025-01-22","cited_by_count":6,"area":"offlinerl"},{"id":"2502.02054","title":"RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation","created":"2025-02-04","cited_by_count":6,"area":"offlinerl"},{"id":"2204.07123","title":"Retrospective on the 2021 BASALT Competition on Learning from Human Feedback","created":"2022-04-14","cited_by_count":5,"area":"alignment"},{"id":"2206.00238","title":"Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble","created":"2022-06-01","cited_by_count":5,"area":"offlinerl"},{"id":"2306.08232","title":"Curricular Subgoals for Inverse Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2309.16074","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","created":"2023-09-28","cited_by_count":5,"area":"offlinerl"},{"id":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2404.08513","title":"Adversarial Imitation Learning via Boosting","created":"2024-04-12","cited_by_count":5,"area":"offlinerl"},{"id":"2404.16989","title":"IDIL: Imitation Learning of Intent-Driven Expert Behavior","created":"2024-04-25","cited_by_count":5,"area":"offlinerl"},{"id":"2406.19626","title":"Safety through feedback in Constrained RL","created":"2024-06-28","cited_by_count":5,"area":null},{"id":"2410.03626","title":"Robust Offline Imitation Learning from Diverse Auxiliary Data","created":"2024-10-04","cited_by_count":5,"area":"offlinerl"},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19946","title":"Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^\\pi$-Realizable MDPs","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2208.04919","title":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","created":"2022-08-09","cited_by_count":4,"area":"offlinerl"},{"id":"2405.12421","title":"A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback","created":"2024-05-20","cited_by_count":4,"area":"alignment"},{"id":"2503.13538","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","created":"2025-03-15","cited_by_count":4,"area":"alignment"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2402.04567","title":"OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences","created":"2024-02-07","cited_by_count":3,"area":"offlinerl"},{"id":"2408.09125","title":"Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning","created":"2024-08-17","cited_by_count":3,"area":"offlinerl"},{"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":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","cited_by_count":3,"area":"offlinerl"}],"next_cursor":"100"}