{"total":67,"rows":[{"id":"2506.12811","title":"Flow-Based Policy for Online Reinforcement Learning","created":"2025-06-15","cited_by_count":37,"area":"deeprl"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2409.00328","title":"Foundations of Multivariate Distributional Reinforcement Learning","created":"2024-08-31","cited_by_count":17,"area":"deeprl"},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"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":"2602.03425","title":"ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning","created":"2026-02-03","cited_by_count":6,"area":"deeprl"},{"id":"2407.15537","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","created":"2024-07-22","cited_by_count":5,"area":"deeprl"},{"id":"2412.16395","title":"Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning","created":"2024-12-20","cited_by_count":4,"area":"deeprl"},{"id":"2501.00364","title":"FORM: Learning Expressive and Transferable First-Order Logic Reward Machines","created":"2024-12-31","cited_by_count":4,"area":"deeprl"},{"id":"2503.17678","title":"Computationally and Sample Efficient Safe Reinforcement Learning Using Adaptive Conformal Prediction","created":"2025-03-22","cited_by_count":4,"area":"deeprl"},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2602.12288","title":"Energy-Aware Reinforcement Learning for Robotic Manipulation of Articulated Components in Infrastructure Operation and Maintenance","created":"2026-01-25","cited_by_count":3,"area":"deeprl"},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2409.11403","title":"UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning","created":"2024-09-17","cited_by_count":2,"area":"deeprl"},{"id":"2411.07087","title":"OCMDP: Observation-Constrained Markov Decision Process","created":"2024-11-11","cited_by_count":2,"area":"deeprl"},{"id":"2501.00884","title":"Diversity Optimization for Travelling Salesman Problem via Deep Reinforcement Learning","created":"2025-01-01","cited_by_count":2,"area":"deeprl"},{"id":"2505.05452","title":"RL-DAUNCE: Reinforcement Learning-Driven Data Assimilation with Uncertainty-Aware Constrained Ensembles","created":"2025-05-08","cited_by_count":2,"area":"deeprl"},{"id":"2508.16474","title":"Reinforcement Learning-based Control via Y-wise Affine Neural Networks (YANNs)","created":"2025-08-22","cited_by_count":2,"area":"deeprl"},{"id":"2510.24272","title":"Survey and Tutorial of Reinforcement Learning Methods in Process Systems Engineering","created":"2025-10-28","cited_by_count":2,"area":"deeprl"},{"id":"2512.00049","title":"Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches","created":"2025-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2406.06184","title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","created":"2024-06-10","cited_by_count":1,"area":"deeprl"},{"id":"2408.07712","title":"Introduction to Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2408.17240","title":"Using Quantum Solved Deep Boltzmann Machines to Increase the Data Efficiency of RL Agents","created":"2024-08-30","cited_by_count":1,"area":"deeprl"},{"id":"2409.08231","title":"Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning","created":"2024-09-12","cited_by_count":1,"area":"deeprl"},{"id":"2410.07612","title":"A Survey for Deep Reinforcement Learning Based Network Intrusion Detection","created":"2024-09-25","cited_by_count":1,"area":"deeprl"},{"id":"2410.16013","title":"Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality","created":"2024-10-21","cited_by_count":1,"area":"deeprl"},{"id":"2411.16120","title":"Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learning","created":"2024-11-25","cited_by_count":1,"area":"deeprl"},{"id":"2501.02221","title":"CORD: Generalizable Cooperation via Role Diversity","created":"2025-01-04","cited_by_count":1,"area":"deeprl"},{"id":"2505.00918","title":"Dynamic and Distributed Routing in IoT Networks based on Multi-Objective Q-Learning","created":"2025-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2505.01979","title":"D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection","created":"2025-05-04","cited_by_count":1,"area":"deeprl"},{"id":"2506.05894","title":"Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2506.21158","title":"Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Design","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2602.09761","title":"Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization","created":"2026-02-10","cited_by_count":1,"area":"deeprl"},{"id":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2407.01333","title":"Deep Reinforcement Learning for Adverse Garage Scenario Generation","created":"2024-07-01","cited_by_count":0,"area":"deeprl"},{"id":"2410.16666","title":"QuasiNav: Asymmetric Cost-Aware Navigation Planning with Constrained Quasimetric Reinforcement Learning","created":"2024-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2412.17908","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2502.01956","title":"DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents","created":"2025-02-04","cited_by_count":0,"area":"deeprl"},{"id":"2502.07280","title":"MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management","created":"2025-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2502.15512","title":"SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning","created":"2025-02-21","cited_by_count":0,"area":"deeprl"},{"id":"2504.07694","title":"Sim-to-Real Transfer in Reinforcement Learning for Maneuver Control of a Variable-Pitch MAV","created":"2025-04-10","cited_by_count":0,"area":"deeprl"},{"id":"2506.00328","title":"BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies","created":"2025-05-31","cited_by_count":0,"area":"deeprl"},{"id":"2507.09540","title":"Learning to Control Dynamical Agents via Spiking Neural Networks and Metropolis-Hastings Sampling","created":"2025-07-13","cited_by_count":0,"area":"deeprl"},{"id":"2507.17893","title":"Action-List Reinforcement Learning Syndrome Decoding for Binary Linear Block Codes","created":"2025-07-23","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":"2510.11491","title":"Constraint-Aware Reinforcement Learning via Adaptive Action Scaling","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.19950","title":"Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets","created":"2025-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2511.02605","title":"Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Learning","created":"2025-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.00427","title":"Hardware-Software Collaborative Computing of Photonic Spiking Reinforcement Learning for Robotic Continuous Control","created":"2025-11-29","cited_by_count":0,"area":"deeprl"},{"id":"2512.03891","title":"Digital Twin-based Control Co-Design of Full Vehicle Active Suspensions via Deep Reinforcement Learning","created":"2025-12-03","cited_by_count":0,"area":"deeprl"},{"id":"2601.04957","title":"Safe Reinforcement Learning Beyond Baseline Control: A Hierarchical Framework for Space Triangle Tethered Formation System","created":"2026-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2601.08662","title":"From Classical to Quantum Reinforcement Learning and Its Applications in Quantum Control: A Beginner's Tutorial","created":"2026-01-13","cited_by_count":0,"area":"deeprl"},{"id":"2603.17309","title":"ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization","created":"2026-03-18","cited_by_count":0,"area":"deeprl"},{"id":"2604.01886","title":"When does learning pay off? A study on DRL-based dynamic algorithm configuration for carbon-aware scheduling","created":"2026-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2604.10812","title":"PokeRL: Reinforcement Learning for Pokemon Red","created":"2026-04-12","cited_by_count":0,"area":"deeprl"},{"id":"2604.26833","title":"Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training","created":"2026-04-29","cited_by_count":0,"area":"deeprl"},{"id":"2605.01978","title":"Stability of Control Lyapunov Function Guided Reinforcement Learning","created":"2026-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2605.12261","title":"Delay-Empowered Causal Hierarchical Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.20037","title":"When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2605.22463","title":"Reinforcement learning for ion shuttling on trapped-ion quantum computers","created":"2026-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2606.19069","title":"Model-Free Reinforcement Learning Control for Resilient Cyber-Physical Systems","created":"2026-06-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.13553","title":"Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement Learning","created":"2026-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2607.18689","title":"Exposure-Based Reinforcement Learning to Rank","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2609.01811","title":"Reinforcement learning to choose optimizers","created":"2026-09-01","cited_by_count":0,"area":"deeprl"},{"id":"2609.13048","title":"MCRL2: Multi-resource Cross-attention-based Representation Learning-augmented Reinforcement Learning for Cloud Microservice Scheduling","created":"2026-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2610.01781","title":"Q-Learning for Reachability in MEC-Free MDPs","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}