{"total":63,"rows":[{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2308.03028","title":"Pre-Trained Large Language Models for Industrial Control","created":"2023-08-06","cited_by_count":16,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"id":"2108.07259","title":"APReL: A Library for Active Preference-based Reward Learning Algorithms","created":"2021-08-16","cited_by_count":14,"area":null},{"id":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2107.06317","title":"Inverse Contextual Bandits: Learning How Behavior Evolves over Time","created":"2021-07-13","cited_by_count":12,"area":null},{"id":"2106.04240","title":"The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation","created":"2021-06-08","cited_by_count":11,"area":null},{"id":"2210.04443","title":"Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2201.04612","title":"Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2503.03921","title":"CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance","created":"2025-03-05","cited_by_count":9,"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":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2410.05063","title":"Control-oriented Clustering of Visual Latent Representation","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2412.07207","title":"MAPLE: A Framework for Active Preference Learning Guided by Large Language Models","created":"2024-12-10","cited_by_count":6,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2104.10610","title":"Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2202.07364","title":"Zero-Shot Assistance in Sequential Decision Problems","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2208.09570","title":"Calculus on MDPs: Potential Shaping as a Gradient","created":"2022-08-20","cited_by_count":4,"area":null},{"id":"2212.01509","title":"Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward","created":"2022-12-03","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":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2210.01800","title":"Bayesian Q-learning With Imperfect Expert Demonstrations","created":"2022-10-01","cited_by_count":3,"area":null},{"id":"2501.01367","title":"Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2502.14160","title":"Efficient Inverse Multiagent Learning","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2202.10153","title":"Inferring Lexicographically-Ordered Rewards from Preferences","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2307.12158","title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2107.02912","title":"Supervised Bayesian Specification Inference from Demonstrations","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2403.06267","title":"FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2502.03717","title":"Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2608.02694","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2101.01366","title":"A Symmetric Loss Perspective of Reliable Machine Learning","created":"2021-01-05","cited_by_count":0,"area":null},{"id":"2103.05343","title":"A model-based framework for learning transparent swarm behaviors","created":"2021-03-09","cited_by_count":0,"area":null},{"id":"2105.03310","title":"Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics","created":"2021-05-07","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":"2312.09865","title":"Automating reward function configuration for drug design","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2410.23554","title":"Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2601.22292","title":"Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.15206","title":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.23562","title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.27421","title":"Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.36924","title":"Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.15401","title":"Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}