{"total":77,"rows":[{"id":"2407.06518","title":"Graph Neural Networks and Deep Reinforcement Learning Based Resource Allocation for V2X Communications","created":"2024-07-09","cited_by_count":18,"area":"deeprl"},{"id":"2404.06492","title":"Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective","created":"2024-04-09","cited_by_count":16,"area":"deeprl"},{"id":"2401.12205","title":"Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization","created":"2024-01-22","cited_by_count":10,"area":"deeprl"},{"id":"2408.03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","created":"2024-08-06","cited_by_count":9,"area":"deeprl"},{"id":"2407.04522","title":"Graph Reinforcement Learning for Power Grids: A Comprehensive Survey","created":"2024-07-05","cited_by_count":7,"area":"deeprl"},{"id":"2501.13448","title":"BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch","created":"2025-01-23","cited_by_count":7,"area":"deeprl"},{"id":"2505.15211","title":"GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2509.16151","title":"Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents","created":"2025-09-19","cited_by_count":7,"area":"deeprl"},{"id":"2405.15831","title":"Transmission Interface Power Flow Adjustment: A Deep Reinforcement Learning Approach based on Multi-task Attribution Map","created":"2024-05-24","cited_by_count":6,"area":"deeprl"},{"id":"2505.03172","title":"Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning","created":"2025-05-06","cited_by_count":6,"area":"deeprl"},{"id":"2401.17914","title":"Attention Graph for Multi-Robot Social Navigation with Deep Reinforcement Learning","created":"2024-01-31","cited_by_count":4,"area":"deeprl"},{"id":"2404.05894","title":"Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning","created":"2024-04-08","cited_by_count":3,"area":"deeprl"},{"id":"2406.07124","title":"CHARME: A chain-based reinforcement learning approach for the minor embedding problem","created":"2024-06-11","cited_by_count":3,"area":"deeprl"},{"id":"2406.17334","title":"Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning","created":"2024-06-25","cited_by_count":3,"area":"deeprl"},{"id":"2407.12794","title":"Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond","created":"2024-06-19","cited_by_count":3,"area":"deeprl"},{"id":"2502.06825","title":"RLOMM: An Efficient and Robust Online Map Matching Framework with Reinforcement Learning","created":"2025-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2502.20326","title":"Deep Reinforcement Learning based Autonomous Decision-Making for Cooperative UAVs: A Search and Rescue Real World Application","created":"2025-02-27","cited_by_count":3,"area":"deeprl"},{"id":"2507.06602","title":"Generalization in Reinforcement Learning for Radio Access Networks","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2510.21809","title":"Embodied Navigation with Auxiliary Task of Action Description Prediction","created":"2025-10-21","cited_by_count":3,"area":"deeprl"},{"id":"2512.08763","title":"Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learning","created":"2025-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2402.00972","title":"Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning","created":"2024-02-01","cited_by_count":2,"area":"deeprl"},{"id":"2404.12633","title":"FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation","created":"2024-04-19","cited_by_count":2,"area":"deeprl"},{"id":"2405.12475","title":"GASE: Graph Attention Sampling with Edges Fusion for Solving Vehicle Routing Problems","created":"2024-05-21","cited_by_count":2,"area":"deeprl"},{"id":"2410.05425","title":"Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search","created":"2024-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2503.20688","title":"Graph-Enhanced Model-Free Reinforcement Learning Agents for Efficient Power Grid Topological Control","created":"2025-03-26","cited_by_count":2,"area":"deeprl"},{"id":"2504.03429","title":"Optimizing Quantum Circuits via ZX Diagrams using Reinforcement Learning and Graph Neural Networks","created":"2025-04-04","cited_by_count":2,"area":"deeprl"},{"id":"2504.19499","title":"Graph Reinforcement Learning for QoS-Aware Load Balancing in Open Radio Access Networks","created":"2025-04-28","cited_by_count":2,"area":"deeprl"},{"id":"2510.16035","title":"RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction","created":"2025-10-16","cited_by_count":2,"area":"deeprl"},{"id":"2511.11870","title":"Graph-Based Imitation and Reinforcement Learning for Efficient Benders Decomposition","created":"2025-11-14","cited_by_count":2,"area":"deeprl"},{"id":"2511.12706","title":"Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs","created":"2025-11-16","cited_by_count":2,"area":"deeprl"},{"id":"2605.14304","title":"Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry","created":"2026-05-14","cited_by_count":2,"area":"deeprl"},{"id":"2401.05610","title":"Graph Q-Learning for Combinatorial Optimization","created":"2024-01-11","cited_by_count":1,"area":"deeprl"},{"id":"2402.06552","title":"Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks","created":"2024-02-09","cited_by_count":1,"area":"deeprl"},{"id":"2402.10074","title":"Class-Balanced and Reinforced Active Learning on Graphs","created":"2024-02-15","cited_by_count":1,"area":"deeprl"},{"id":"2403.14879","title":"Learning to Change: Choreographing Mixed Traffic Through Lateral Control and Hierarchical Reinforcement Learning","created":"2024-03-21","cited_by_count":1,"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":"2406.11452","title":"Attention-Based Deep Reinforcement Learning for Qubit Allocation in Modular Quantum Architectures","created":"2024-06-17","cited_by_count":1,"area":"deeprl"},{"id":"2408.07945","title":"Solving a Rubik's Cube Using its Local Graph Structure","created":"2024-08-15","cited_by_count":1,"area":"deeprl"},{"id":"2410.23396","title":"Adaptive Network Intervention for Complex Systems: A Hierarchical Graph Reinforcement Learning Approach","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2411.17353","title":"Joint Combinatorial Node Selection and Resource Allocations in the Lightning Network using Attention-based Reinforcement Learning","created":"2024-11-26","cited_by_count":1,"area":"deeprl"},{"id":"2501.16130","title":"ReFill: Reinforcement Learning for Fill-In Minimization","created":"2025-01-27","cited_by_count":1,"area":"deeprl"},{"id":"2503.22775","title":"Invariant Control Strategies for Active Flow Control using Graph Neural Networks","created":"2025-03-28","cited_by_count":1,"area":"deeprl"},{"id":"2504.14412","title":"Quantum-Enhanced Reinforcement Learning for Power Grid Security Assessment","created":"2025-04-19","cited_by_count":1,"area":"deeprl"},{"id":"2505.12902","title":"Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning Approach","created":"2025-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2507.13920","title":"Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem","created":"2025-07-18","cited_by_count":1,"area":"deeprl"},{"id":"2602.14344","title":"Zero-Shot Instruction Following in RL via Structured LTL Representations","created":"2026-02-15","cited_by_count":1,"area":"deeprl"},{"id":"2406.14697","title":"A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2411.16134","title":"Multi-Robot Reliable Navigation in Uncertain Topological Environments with Graph Attention Networks","created":"2024-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2503.08867","title":"Zero-Shot Action Generalization with Limited Observations","created":"2025-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2505.13986","title":"RIDGECUT: Learning Graph Partitioning with Rings and Wedges","created":"2025-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2505.16471","title":"Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization","created":"2025-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2507.19234","title":"Virne: A Comprehensive Benchmark for RL-based Network Resource Allocation in NFV","created":"2025-07-25","cited_by_count":0,"area":"deeprl"},{"id":"2509.10526","title":"Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning","created":"2025-09-04","cited_by_count":0,"area":"deeprl"},{"id":"2509.14431","title":"Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control","created":"2025-09-17","cited_by_count":0,"area":"deeprl"},{"id":"2512.02633","title":"Zero-Shot Instruction Following in RL via Structured LTL Representations","created":"2025-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2512.11342","title":"DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning","created":"2025-12-12","cited_by_count":0,"area":"deeprl"},{"id":"2512.18540","title":"Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies","created":"2025-12-20","cited_by_count":0,"area":"deeprl"},{"id":"2512.19696","title":"QoS-Aware Dynamic CU Selection in O-RAN with Graph-Based Reinforcement Learning","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2601.06664","title":"Reinforcement Learning-Guided Dynamic Multi-Graph Fusion for Evacuation Traffic Prediction","created":"2026-01-10","cited_by_count":0,"area":"deeprl"},{"id":"2601.07948","title":"Reinforcement Learning Methods for Neighborhood Selection in Local Search","created":"2026-01-12","cited_by_count":0,"area":"deeprl"},{"id":"2603.06278","title":"Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport","created":"2026-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2603.18314","title":"Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learning","created":"2026-03-18","cited_by_count":0,"area":"deeprl"},{"id":"2604.09202","title":"On the Role of DAG topology in Energy-Aware Cloud Scheduling : A GNN-Based Deep Reinforcement Learning Approach","created":"2026-04-10","cited_by_count":0,"area":"deeprl"},{"id":"2604.25848","title":"A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2604.26566","title":"Learning to Route Electric Trucks Under Operational Uncertainty","created":"2026-04-29","cited_by_count":0,"area":"deeprl"},{"id":"2605.14501","title":"Fully Dynamic Rebalancing in Dockless Bike-Sharing Systems via Deep Reinforcement Learning","created":"2026-05-14","cited_by_count":0,"area":"deeprl"},{"id":"2605.22142","title":"Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability","created":"2026-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2606.12816","title":"Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing","created":"2026-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2607.04091","title":"Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks","created":"2026-07-05","cited_by_count":0,"area":"deeprl"},{"id":"2607.08703","title":"MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2607.18368","title":"Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability","created":"2026-07-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.25082","title":"PLATO: Pointer Learner for Agent and Task Openness","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.30162","title":"Reinforcement Learning for Symbolic Equation Solving","created":"2026-08-31","cited_by_count":0,"area":"deeprl"},{"id":"2609.02538","title":"A Comparative Study of Graph Representations for GNN-Based Power Grid Control in L2RPN","created":"2026-09-02","cited_by_count":0,"area":"deeprl"},{"id":"2609.25397","title":"Deep Reinforcement Learning on Item-Compatibility Graphs for One-Dimensional Bin Packing","created":"2026-09-21","cited_by_count":0,"area":"deeprl"},{"id":"2609.34553","title":"Verifying Neural Networks with Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.20224","title":"Design Space Exploration of Reinforcement Learning Configurations for Post-Legalization Placement","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}