{"total":62,"rows":[{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156,"area":"mllm"},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99,"area":null},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2503.11240","title":"Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards","created":"2025-03-14","cited_by_count":32,"area":"diffusion"},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"id":"2410.14660","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","created":"2024-10-18","cited_by_count":30,"area":"alignment"},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"id":"2411.05273","title":"Real-World Offline Reinforcement Learning from Vision Language Model Feedback","created":"2024-11-08","cited_by_count":22,"area":"mllm"},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2310.13565","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","created":"2023-10-20","cited_by_count":19,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2509.18056","title":"TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs","created":"2025-09-22","cited_by_count":15,"area":"mllm"},{"id":"2212.03175","title":"Learning Representations that Enable Generalization in Assistive Tasks","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2506.18631","title":"ReDit: Reward Dithering for Improved LLM Policy Optimization","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2407.16186","title":"Automatic Environment Shaping is the Next Frontier in RL","created":"2024-07-23","cited_by_count":7,"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":"2410.16632","title":"Benchmarking Smoothness and Reducing High-Frequency Oscillations in Continuous Control Policies","created":"2024-10-22","cited_by_count":7,"area":"deeprl"},{"id":"2412.16878","title":"Online Preference-based Reinforcement Learning with Self-augmented Feedback from Large Language Model","created":"2024-12-22","cited_by_count":7,"area":"alignment"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2311.10026","title":"Guaranteeing Control Requirements via Reward Shaping in Reinforcement Learning","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2406.18293","title":"Combining Automated Optimisation of Hyperparameters and Reward Shape","created":"2024-06-26","cited_by_count":5,"area":"deeprl"},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2503.15724","title":"Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning","created":"2025-03-19","cited_by_count":4,"area":"deeprl"},{"id":"2506.22365","title":"Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation","created":"2025-06-27","cited_by_count":4,"area":"deeprl"},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"area":"lr"},{"id":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2410.03847","title":"Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping","created":"2024-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2501.00989","title":"Bootstrapped Reward Shaping","created":"2025-01-02","cited_by_count":3,"area":"deeprl"},{"id":"2511.13765","title":"PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning","created":"2025-11-14","cited_by_count":3,"area":"alignment"},{"id":"2312.09983","title":"Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping","created":"2023-12-15","cited_by_count":2,"area":"offlinerl"},{"id":"2406.13453","title":"Reinforcement Learning to improve delta robot throws for sorting scrap metal","created":"2024-06-19","cited_by_count":2,"area":"deeprl"},{"id":"2409.08724","title":"Quasimetric Value Functions with Dense Rewards","created":"2024-09-13","cited_by_count":2,"area":"deeprl"},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2509.24129","title":"Mash, Spread, Slice! Learning to Manipulate Object States via Visual Spatial Progress","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2307.05209","title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2309.14096","title":"Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2310.10610","title":"Quantifying Assistive Robustness Via the Natural-Adversarial Frontier","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2404.01598","title":"Extremum-Seeking Action Selection for Accelerating Policy Optimization","created":"2024-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2404.07826","title":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2407.03311","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","created":"2024-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2504.19480","title":"An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2307.09109","title":"Mining of Single-Class by Active Learning for Semantic Segmentation","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2401.14226","title":"Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks","created":"2024-01-25","cited_by_count":0,"area":"deeprl"},{"id":"2403.14110","title":"Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method","created":"2024-03-21","cited_by_count":0,"area":"deeprl"},{"id":"2501.19102","title":"Reinforcement Learning on Reconfigurable Hardware: Overcoming Material Variability in Laser Material Processing","created":"2025-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2503.24296","title":"Fair Dynamic Spectrum Access via Fully Decentralized Multi-Agent Reinforcement Learning","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2510.10202","title":"Performance Index Shaping for Closed-loop Optimal Control","created":"2025-10-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.15796","title":"Cavity Duplexer Tuning with 1d Resnet-like Neural Networks","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2510.19528","title":"Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2603.06565","title":"Boosting deep Reinforcement Learning using pretraining with Logical Options","created":"2026-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2607.00483","title":"VLM-AR3L: Vision-Language Models for Absolute and Relative Rewards in Reinforcement Learning","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.17317","title":"TAPAS: Throughput-adaptive Perception for Autonomous Systems","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2607.19616","title":"The Mechanism Matters: When Knowledge Graphs Help Reinforcement Learning","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2608.08158","title":"A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning","created":"2026-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2608.11239","title":"Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2610.01789","title":"iADD: Improving Alignment and Diversity in Diffusion Policy Optimization","created":"2026-10-01","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}