{"total":105,"rows":[{"id":"2505.15201","title":"Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems","created":"2025-05-21","cited_by_count":87,"area":"deeprl"},{"id":"2510.14830","title":"RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning","created":"2025-10-16","cited_by_count":59,"area":"deeprl"},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"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":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"id":"2403.01410","title":"Barrier Functions Inspired Reward Shaping for Reinforcement Learning","created":"2024-03-03","cited_by_count":11,"area":"deeprl"},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2503.17644","title":"On The Sample Complexity Bounds In Bilevel Reinforcement Learning","created":"2025-03-22","cited_by_count":10,"area":"deeprl"},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2404.12754","title":"Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation","created":"2024-04-19","cited_by_count":7,"area":"deeprl"},{"id":"2405.15541","title":"Learning Generalizable Human Motion Generator with Reinforcement Learning","created":"2024-05-24","cited_by_count":7,"area":"deeprl"},{"id":"2503.18549","title":"RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation","created":"2025-03-24","cited_by_count":7,"area":"deeprl"},{"id":"2507.14066","title":"Preference-based Multi-Objective Reinforcement Learning","created":"2025-07-18","cited_by_count":7,"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":"2407.04803","title":"The Impact of Quantization and Pruning on Deep Reinforcement Learning Models","created":"2024-07-05","cited_by_count":6,"area":"deeprl"},{"id":"2410.13837","title":"ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization","created":"2024-10-17","cited_by_count":6,"area":"deeprl"},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2606.30376","title":"FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification","created":"2026-06-29","cited_by_count":6,"area":"deeprl"},{"id":"2401.02160","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","created":"2024-01-04","cited_by_count":4,"area":"deeprl"},{"id":"2403.08152","title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","created":"2024-03-13","cited_by_count":4,"area":"deeprl"},{"id":"2403.18539","title":"Safe and Robust Reinforcement Learning: Principles and Practice","created":"2024-03-27","cited_by_count":4,"area":"deeprl"},{"id":"2408.12130","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","created":"2024-08-22","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":"2506.15825","title":"Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters","created":"2025-06-18","cited_by_count":4,"area":"deeprl"},{"id":"2510.18340","title":"Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs","created":"2025-10-21","cited_by_count":4,"area":"deeprl"},{"id":"2405.17287","title":"Opinion-Guided Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"deeprl"},{"id":"2505.11661","title":"Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2506.00388","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2605.15971","title":"OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation","created":"2026-05-15","cited_by_count":3,"area":"deeprl"},{"id":"2405.01760","title":"Reinforcement Learning-Guided Semi-Supervised Learning","created":"2024-05-02","cited_by_count":2,"area":"deeprl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"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":"2503.01468","title":"Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimization","created":"2025-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2504.05393","title":"Interactive Explanations for Reinforcement-Learning Agents","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2507.11706","title":"Reinforcement Learning from Adversarial Preferences in Tabular MDPs","created":"2025-07-15","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":"2603.27944","title":"Flip Stunts on Bicycle Robots using Iterative Motion Imitation","created":"2026-03-30","cited_by_count":2,"area":"deeprl"},{"id":"2606.03949","title":"Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation","created":"2026-06-02","cited_by_count":2,"area":"deeprl"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2607.00442","title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","created":"2026-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2405.14244","title":"Tell me why: Training preferences-based RL with human preferences and step-level explanations","created":"2024-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2406.13869","title":"Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning","created":"2024-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2409.03301","title":"ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models","created":"2024-09-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.07502","title":"Human-Inspired Multi-Level Reinforcement Learning","created":"2025-01-13","cited_by_count":1,"area":"deeprl"},{"id":"2504.21731","title":"Adaptive 3D UI Placement in Mixed Reality Using Deep Reinforcement Learning","created":"2025-04-30","cited_by_count":1,"area":"deeprl"},{"id":"2505.06357","title":"DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition","created":"2025-05-09","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":"2509.20541","title":"Selective Progress-Aware Querying for Human-in-the-Loop Reinforcement Learning","created":"2025-09-24","cited_by_count":1,"area":"deeprl"},{"id":"2509.24305","title":"Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning","created":"2025-09-29","cited_by_count":1,"area":"deeprl"},{"id":"2512.06533","title":"Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2512.13399","title":"Dual-Evolving Reinforcement Learning for Automated Reward Design","created":"2025-12-15","cited_by_count":1,"area":"deeprl"},{"id":"2602.04518","title":"Learning the Value Systems of Agents with Preference-based and Inverse Reinforcement Learning","created":"2026-02-04","cited_by_count":1,"area":"deeprl"},{"id":"2603.01694","title":"MVR: Multi-view Video Reward Shaping for Reinforcement Learning","created":"2026-03-02","cited_by_count":1,"area":"deeprl"},{"id":"2603.22273","title":"Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration","created":"2026-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2603.28053","title":"Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2605.00384","title":"PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learning","created":"2026-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2605.13641","title":"Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization","created":"2026-05-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.22123","title":"Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations","created":"2026-05-21","cited_by_count":1,"area":"deeprl"},{"id":"2606.23640","title":"Learning Process Rewards via Success Visitation Matching for Efficient RL","created":"2026-06-22","cited_by_count":1,"area":"deeprl"},{"id":"2608.10996","title":"ConRub-Med: Reinforcement Learning with Consensus Rubrics for Open-Ended Medical Question Answering","created":"2026-08-11","cited_by_count":1,"area":"deeprl"},{"id":"2608.15707","title":"GAINS: Leveraging Inconsistent Human Intervention Signals in Reinforcement Learning","created":"2026-08-16","cited_by_count":1,"area":"deeprl"},{"id":"2405.08380","title":"CIER: A Novel Experience Replay Approach with Causal Inference in Deep Reinforcement Learning","created":"2024-05-14","cited_by_count":0,"area":"deeprl"},{"id":"2406.06495","title":"Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity","created":"2024-06-10","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":"2407.07288","title":"Structural Design Through Reinforcement Learning","created":"2024-07-10","cited_by_count":0,"area":"deeprl"},{"id":"2408.16776","title":"Online Behavior Modification for Expressive User Control of RL-Trained Robots","created":"2024-08-15","cited_by_count":0,"area":"deeprl"},{"id":"2504.12557","title":"TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels","created":"2025-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2504.17006","title":"A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2505.19682","title":"Deep Actor-Critics with Tight Risk Certificates","created":"2025-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2506.06959","title":"Deontically Constrained Policy Improvement in Reinforcement Learning Agents","created":"2025-06-08","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":"2507.04730","title":"CueLearner: Bootstrapping and local policy adaptation from relative feedback","created":"2025-07-07","cited_by_count":0,"area":"deeprl"},{"id":"2507.13491","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","created":"2025-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2508.18817","title":"Learning Acrobatic Flight from Preferences","created":"2025-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2508.19132","title":"Active Query Selection for Crowd-Based Reinforcement Learning","created":"2025-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.06545","title":"Incoherence in Goal-Conditioned Autoregressive Models","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2510.07624","title":"From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2511.07904","title":"Test-driven Reinforcement Learning in Continuous Control","created":"2025-11-11","cited_by_count":0,"area":"deeprl"},{"id":"2511.18878","title":"Accelerating Reinforcement Learning via Error-Related Human Brain Signals","created":"2025-11-24","cited_by_count":0,"area":"deeprl"},{"id":"2511.19808","title":"Learning to Clean: Reinforcement Learning for Noisy Label Correction","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2512.16446","title":"E-SDS: Environment-aware See it, Do it, Sorted - Automated Environment-Aware Reinforcement Learning for Humanoid Locomotion","created":"2025-12-18","cited_by_count":0,"area":"deeprl"},{"id":"2512.18317","title":"Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air Systems","created":"2025-12-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.12053","title":"A New Strategy for Artificial Intelligence: Training Foundation Models Directly on Human Brain Data","created":"2026-01-17","cited_by_count":0,"area":"deeprl"},{"id":"2601.18580","title":"K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents","created":"2026-01-26","cited_by_count":0,"area":"deeprl"},{"id":"2602.05379","title":"Variance Reduction Based Experience Replay for Policy Optimization","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2602.08835","title":"Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2603.23565","title":"Safe Reinforcement Learning with Preference-based Constraint Inference","created":"2026-03-24","cited_by_count":0,"area":"deeprl"},{"id":"2603.29369","title":"AP-DRL: A Synergistic Algorithm-Hardware Framework for Automatic Task Partitioning of Deep Reinforcement Learning on Versal ACAP","created":"2026-03-31","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":"2604.25191","title":"How Can Reinforcement Learning Achieve Expert-level Placement?","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.23565","title":"Understanding Goal Generalisation in Sequential Reinforcement Learning","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.25739","title":"The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible","created":"2026-05-25","cited_by_count":0,"area":"deeprl"},{"id":"2606.00367","title":"Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.11982","title":"PAWS: Preference Learning with Advantage-Weighted Segments","created":"2026-06-10","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}