{"total":58,"rows":[{"id":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490,"area":"driving"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2402.16075","title":"Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion","created":"2024-02-25","cited_by_count":21,"area":"diffusion"},{"id":"2410.08852","title":"Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback","created":"2024-10-11","cited_by_count":11,"area":"alignment"},{"id":"2408.10504","title":"QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning","created":"2024-08-20","cited_by_count":10,"area":"offlinerl"},{"id":"2205.03484","title":"Diverse Imitation Learning via Self-Organizing Generative Models","created":"2022-05-06","cited_by_count":5,"area":"offlinerl"},{"id":"2412.04189","title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2509.04853","title":"A Knowledge-Driven Diffusion Policy for End-to-End Autonomous Driving Based on Expert Routing","created":"2025-09-05","cited_by_count":5,"area":"diffusion"},{"id":"2503.21406","title":"Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning","created":"2025-03-27","cited_by_count":4,"area":"offlinerl"},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"},{"id":"2403.00550","title":"Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking","created":"2024-03-01","cited_by_count":3,"area":"offlinerl"},{"id":"2405.09760","title":"Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning","created":"2024-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2406.04913","title":"Online Adaptation for Enhancing Imitation Learning Policies","created":"2024-06-07","cited_by_count":3,"area":"offlinerl"},{"id":"2407.21713","title":"Social Learning through Interactions with Other Agents: A Survey","created":"2024-07-31","cited_by_count":3,"area":null},{"id":"2603.25968","title":"Neuro-Cognitive Reward Modeling for Human-Centered Autonomous Vehicle Control","created":"2026-03-26","cited_by_count":3,"area":"driving"},{"id":"2308.15969","title":"Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification","created":"2023-08-30","cited_by_count":2,"area":"alignment"},{"id":"2404.13348","title":"Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2503.23650","title":"A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective","created":"2025-03-31","cited_by_count":2,"area":"driving"},{"id":"2504.05950","title":"AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2508.21501","title":"Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting","created":"2025-08-29","cited_by_count":2,"area":"offlinerl"},{"id":"2301.01088","title":"Explaining Imitation Learning through Frames","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2301.07182","title":"Genetic Imitation Learning by Reward Extrapolation","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2311.17693","title":"Toward a Surgeon-in-the-Loop Ophthalmic Robotic Apprentice using Reinforcement and Imitation Learning","created":"2023-11-29","cited_by_count":1,"area":"offlinerl"},{"id":"2403.16075","title":"IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History","created":"2024-03-24","cited_by_count":1,"area":"offlinerl"},{"id":"2403.20250","title":"Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failures","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2405.10576","title":"An Efficient Learning Control Framework With Sim-to-Real for String-Type Artificial Muscle-Driven Robotic Systems","created":"2024-05-17","cited_by_count":1,"area":"deeprl"},{"id":"2406.08472","title":"RILe: Reinforced Imitation Learning","created":"2024-06-12","cited_by_count":1,"area":"offlinerl"},{"id":"2411.08637","title":"Robot See, Robot Do: Imitation Reward for Noisy Financial Environments","created":"2024-11-13","cited_by_count":1,"area":"offlinerl"},{"id":"2501.00078","title":"Human-like Bots for Tactical Shooters Using Compute-Efficient Sensors","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2503.01363","title":"FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interaction","created":"2025-03-03","cited_by_count":1,"area":"offlinerl"},{"id":"2503.05229","title":"Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving","created":"2025-03-07","cited_by_count":1,"area":"diffusion"},{"id":"2510.14467","title":"Restoring Noisy Demonstration for Imitation Learning With Diffusion Models","created":"2025-10-16","cited_by_count":1,"area":"diffusion"},{"id":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2603.10929","title":"Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment","created":"2026-03-11","cited_by_count":1,"area":"offlinerl"},{"id":"2607.03865","title":"High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching","created":"2026-07-04","cited_by_count":1,"area":"diffusion"},{"id":"2209.04100","title":"Task-Agnostic Learning to Accomplish New Tasks","created":"2022-09-09","cited_by_count":0,"area":"offlinerl"},{"id":"2304.10914","title":"Self-Supervised Adversarial Imitation Learning","created":"2023-04-21","cited_by_count":0,"area":"offlinerl"},{"id":"2307.08532","title":"LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2312.05759","title":"Beyond One Model Fits All: Ensemble Deep Learning for Autonomous Vehicles","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2401.11396","title":"Visual Imitation Learning with Calibrated Contrastive Representation","created":"2024-01-21","cited_by_count":0,"area":"offlinerl"},{"id":"2402.18836","title":"A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations","created":"2024-02-29","cited_by_count":0,"area":"deeprl"},{"id":"2407.06485","title":"CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2407.21244","title":"VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections","created":"2024-07-30","cited_by_count":0,"area":"offlinerl"},{"id":"2409.07189","title":"AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systems","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2410.07404","title":"Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models","created":"2024-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2411.00995","title":"Safe Imitation Learning-based Optimal Energy Storage Systems Dispatch in Distribution Networks","created":"2024-11-01","cited_by_count":0,"area":"offlinerl"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2412.07617","title":"Swarm Behavior Cloning","created":"2024-12-10","cited_by_count":0,"area":"offlinerl"},{"id":"2501.14942","title":"Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2509.19379","title":"Learning from Observation: A Survey of Recent Advances","created":"2025-09-20","cited_by_count":0,"area":"offlinerl"},{"id":"2511.00002","title":"VRScout: Towards Real-Time, Autonomous Testing of Virtual Reality Games","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.03565","title":"Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2512.11839","title":"Grounding Large Language Models as Generalizable Policies in Network Control","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.05383","title":"Imitation Learning for Combinatorial Optimisation under Uncertainty","created":"2026-01-08","cited_by_count":0,"area":"offlinerl"},{"id":"2602.15816","title":"Developing AI Agents with Simulated Data: Why, what, and how?","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2607.17003","title":"Scalable Causal Imitation Learning","created":"2026-07-18","cited_by_count":0,"area":"offlinerl"},{"id":"2608.07398","title":"Uncovering expert objectives in production planning via inverse optimization: An industrial case study","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}