{"total":52,"rows":[{"id":"2103.16817","title":"Learning Generalizable Robotic Reward Functions from \"In-The-Wild\" Human Videos","created":"2021-03-31","cited_by_count":119,"area":null},{"id":"2111.04850","title":"Dueling RL: Reinforcement Learning with Trajectory Preferences","created":"2021-11-08","cited_by_count":106,"area":null},{"id":"2103.12656","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","created":"2021-03-23","cited_by_count":38,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2308.05731","title":"The Integration of Prediction and Planning in Deep Learning Automated Driving Systems: A Review","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25,"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":"2212.09902","title":"Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance","created":"2022-12-19","cited_by_count":23,"area":null},{"id":"2211.13837","title":"End-to-End Stochastic Optimization with Energy-Based Model","created":"2022-11-25","cited_by_count":19,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"id":"2109.10312","title":"Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks","created":"2021-09-21","cited_by_count":13,"area":null},{"id":"2107.13507","title":"The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior","created":"2021-07-28","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2309.15302","title":"STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience","created":"2023-09-26","cited_by_count":11,"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":"2401.14424","title":"Discovering Mathematical Formulas from Data via GPT-guided Monte Carlo Tree Search","created":"2024-01-24","cited_by_count":10,"area":null},{"id":"2407.14872","title":"Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts","created":"2024-07-20","cited_by_count":10,"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":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2412.04758","title":"Measuring Goal-Directedness","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2112.05495","title":"How Private Is Your RL Policy? An Inverse RL Based Analysis Framework","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2303.05487","title":"Learning Rational Subgoals from Demonstrations and Instructions","created":"2023-03-09","cited_by_count":5,"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":"2407.15086","title":"MaxMI: A Maximal Mutual Information Criterion for Manipulation Concept Discovery","created":"2024-07-21","cited_by_count":5,"area":null},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2109.07788","title":"Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2210.03582","title":"Learning Social Navigation from Demonstrations with Conditional Neural Processes","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2301.12776","title":"PAC-Bayesian Soft Actor-Critic Learning","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2410.01458","title":"From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge","created":"2024-10-02","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":"2305.10548","title":"Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2503.13432","title":"Uncovering Utility Functions from Observed Outcomes","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2604.25136","title":"Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment","created":"2026-04-28","cited_by_count":2,"area":null},{"id":"2112.15521","title":"Inferring perceptual decision making parameters from behavior in production and reproduction tasks","created":"2021-12-31","cited_by_count":1,"area":null},{"id":"2308.08017","title":"Active Inverse Learning in Stackelberg Trajectory Games","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2409.13299","title":"OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2409.18102","title":"MALPOLON: A Framework for Deep Species Distribution Modeling","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2501.18803","title":"Deceptive Sequential Decision-Making via Regularized Policy Optimization","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2504.18235","title":"BiasBench: A reproducible benchmark for tuning the biases of event cameras","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2109.00414","title":"Balancing Performance and Human Autonomy with Implicit Guidance Agent","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2111.07489","title":"Deep Learning based Urban Vehicle Trajectory Analytics","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2205.10431","title":"Learning Dense Reward with Temporal Variant Self-Supervision","created":"2022-05-20","cited_by_count":0,"area":null},{"id":"2405.15975","title":"Inference of Utilities and Time Preference in Sequential Decision-Making","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2511.05640","title":"Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2602.02838","title":"Beyond Content: Behavioral Policies Reveal Actors in Information Operations","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.16099","title":"Quantifying and Attributing Submodel Uncertainty in Stochastic Simulation Models and Digital Twins","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2602.20152","title":"Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2608.11419","title":"Diffusion-Based Data-Driven Assortment Optimization","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.26135","title":"VACS: Value-Aligned Compositional Shielding for Multi-Agent Reasoning","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}