{"total":17,"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":"2510.14837","title":"Reinforcement Learning with Stochastic Reward Machines","created":"2025-10-16","cited_by_count":7,"area":"deeprl"},{"id":"2403.08906","title":"Strategizing against Q-learners: A Control-theoretical Approach","created":"2024-03-13","cited_by_count":2,"area":"deeprl"},{"id":"2510.20314","title":"Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2602.08092","title":"Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities","created":"2026-02-08","cited_by_count":2,"area":"deeprl"},{"id":"2407.16842","title":"Adapting Image-based RL Policies via Predicted Rewards","created":"2024-07-23","cited_by_count":1,"area":"deeprl"},{"id":"2503.00206","title":"Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery Approach","created":"2025-02-28","cited_by_count":1,"area":"deeprl"},{"id":"2503.04219","title":"Quantum-Inspired Reinforcement Learning in the Presence of Epistemic Ambivalence","created":"2025-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2506.08737","title":"Exploration by Random Reward Perturbation","created":"2025-06-10","cited_by_count":1,"area":"deeprl"},{"id":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2404.13879","title":"Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty","created":"2024-04-22","cited_by_count":0,"area":"deeprl"},{"id":"2502.19356","title":"Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planning","created":"2025-02-26","cited_by_count":0,"area":"deeprl"},{"id":"2505.00382","title":"Approximation to Deep Q-Network by Stochastic Delay Differential Equations","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2506.21127","title":"Meta Policy Switching for Secure UAV Deconfliction in Adversarial Airspace","created":"2025-06-26","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":"2602.18856","title":"Issues with Measuring Task Complexity via Random Policies in Robotic Tasks","created":"2026-02-21","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}