{"total":21,"rows":[{"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":"2411.02623","title":"Learning to Assist Humans without Inferring Rewards","created":"2024-11-04","cited_by_count":13,"area":"deeprl"},{"id":"2411.17764","title":"PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement","created":"2024-11-26","cited_by_count":13,"area":"deeprl"},{"id":"2405.00746","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","created":"2024-04-30","cited_by_count":6,"area":"deeprl"},{"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":"2506.03066","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","created":"2025-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2409.07268","title":"Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences","created":"2024-09-11","cited_by_count":2,"area":"deeprl"},{"id":"2501.19128","title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach","created":"2025-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2408.11328","title":"Fast State Stabilization using Deep Reinforcement Learning for Measurement-based Quantum Feedback Control","created":"2024-08-21","cited_by_count":1,"area":"deeprl"},{"id":"2507.03068","title":"Mitigating Goal Misgeneralization via Minimax Regret","created":"2025-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2508.14027","title":"Learning from Preferences and Mixed Demonstrations in General Settings","created":"2025-08-19","cited_by_count":1,"area":"deeprl"},{"id":"2511.15199","title":"Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking","created":"2025-11-19","cited_by_count":1,"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":"2407.06503","title":"Preference-Guided Reinforcement Learning for Efficient Exploration","created":"2024-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2506.13741","title":"PB$^2$: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2507.11875","title":"DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation","created":"2025-07-16","cited_by_count":0,"area":"deeprl"},{"id":"2510.07715","title":"Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning","created":"2025-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2602.08582","title":"SemiNFT: Learning to Transfer Presets from Imitation to Appreciation via Hybrid-Sample Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2604.04251","title":"MC-CPO: Mastery-Conditioned Constrained Policy Optimization for Pedagogically Safe Intelligent Tutoring Systems","created":"2026-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.01260","title":"PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}