{"total":80,"rows":[{"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":"2410.17647","title":"Entity-based Reinforcement Learning for Autonomous Cyber Defence","created":"2024-10-23","cited_by_count":11,"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":"2509.16151","title":"Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents","created":"2025-09-19","cited_by_count":7,"area":"deeprl"},{"id":"2402.13946","title":"AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning","created":"2024-02-21","cited_by_count":6,"area":"deeprl"},{"id":"2509.05397","title":"RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement Learning","created":"2025-09-05","cited_by_count":5,"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":"2409.05344","title":"GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2410.15184","title":"Action abstractions for amortized sampling","created":"2024-10-19","cited_by_count":4,"area":"deeprl"},{"id":"2406.15025","title":"SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learning","created":"2024-06-21","cited_by_count":3,"area":"deeprl"},{"id":"2406.15096","title":"Towards General Negotiation Strategies with End-to-End Reinforcement Learning","created":"2024-06-21","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":"2502.20326","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":"2503.10421","title":"Learning Constraints-Based Adaptive Hypergraph Neural Networks for Solving Vehicle Routing Problems","created":"2025-03-13","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":"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":"2407.01615","title":"Edge-DIRECT: A Deep Reinforcement Learning-based Method for Solving Heterogeneous Electric Vehicle Routing Problem with Time Window Constraints","created":"2024-06-28","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":"2506.04505","title":"SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning","created":"2025-06-04","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":"2601.20753","title":"GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning","created":"2026-01-28","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":"2402.14236","title":"Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning","created":"2024-02-22","cited_by_count":1,"area":"deeprl"},{"id":"2407.10987","title":"Adaptive Digital Twin and Communication-Efficient Federated Learning Network Slicing for 5G-enabled Internet of Things","created":"2024-06-22","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":"2503.16371","title":"Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming","created":"2025-03-20","cited_by_count":1,"area":"deeprl"},{"id":"2504.02383","title":"Reinforcement Learning for Solving the Pricing Problem in Column Generation: Applications to Vehicle Routing","created":"2025-04-03","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":"2508.00141","title":"INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks","created":"2025-07-31","cited_by_count":1,"area":"deeprl"},{"id":"2511.02217","title":"Optimizing Multi-Lane Intersection Performance in Mixed Autonomy Environments","created":"2025-11-04","cited_by_count":1,"area":"deeprl"},{"id":"2512.01518","title":"End-to-end Deep Reinforcement Learning for Stochastic Multi-objective Optimization in C-VRPTW","created":"2025-12-01","cited_by_count":1,"area":"deeprl"},{"id":"2601.03646","title":"ReLA: Representation Learning and Aggregation for Job Scheduling with Reinforcement Learning","created":"2026-01-07","cited_by_count":1,"area":"deeprl"},{"id":"2404.01557","title":"Distributed Autonomous Swarm Formation for Dynamic Network Bridging","created":"2024-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2406.05041","title":"Online Frequency Scheduling by Learning Parallel Actions","created":"2024-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2406.14214","title":"REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2408.07578","title":"A Nested Graph Reinforcement Learning-based Decision-making Strategy for Eco-platooning","created":"2024-08-14","cited_by_count":0,"area":"deeprl"},{"id":"2409.07932","title":"Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies","created":"2024-09-12","cited_by_count":0,"area":"deeprl"},{"id":"2410.23753","title":"Enhancing Chess Reinforcement Learning with Graph Representation","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2412.17252","title":"A Coalition Game for On-demand Multi-modal 3D Automated Delivery System","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2412.19578","title":"Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization","created":"2024-12-27","cited_by_count":0,"area":"deeprl"},{"id":"2501.19063","title":"Optimizing Job Allocation using Reinforcement Learning with Graph Neural Networks","created":"2025-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2502.14741","title":"Reinforcement Learning with Graph Attention for Routing and Wavelength Assignment with Lightpath Reuse","created":"2025-02-20","cited_by_count":0,"area":"deeprl"},{"id":"2503.07678","title":"Using a single actor to output personalized policy for different intersections","created":"2025-03-10","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":"2506.06204","title":"How to craft a deep reinforcement learning policy for wind farm flow control","created":"2025-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2506.16764","title":"Reinforcement Learning for Hybrid Charging Stations Planning and Operation Considering Fixed and Mobile Chargers","created":"2025-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2508.06863","title":"Energy Efficient Task Offloading in UAV-Enabled MEC Using a Fully Decentralized Deep Reinforcement Learning Approach","created":"2025-08-09","cited_by_count":0,"area":"deeprl"},{"id":"2509.06108","title":"Using Reinforcement Learning to Optimize the Global and Local Crossing Number","created":"2025-09-07","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":"2509.12863","title":"GRATE: a Graph transformer-based deep Reinforcement learning Approach for Time-efficient autonomous robot Exploration","created":"2025-09-16","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":"2511.16929","title":"CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2512.18146","title":"On Swarm Leader Identification using Probing Policies","created":"2025-12-20","cited_by_count":0,"area":"deeprl"},{"id":"2512.24284","title":"DRL-TH: Jointly Utilizing Temporal Graph Attention and Hierarchical Fusion for UGV Navigation in Crowded Environments","created":"2025-12-30","cited_by_count":0,"area":"deeprl"},{"id":"2601.03686","title":"Dual-Attention Heterogeneous GNN for Multi-robot Collaborative Area Search via Deep Reinforcement Learning","created":"2026-01-07","cited_by_count":0,"area":"deeprl"},{"id":"2601.15131","title":"Vehicle Routing with Finite Time Horizon using Deep Reinforcement Learning with Improved Network Embedding","created":"2026-01-21","cited_by_count":0,"area":"deeprl"},{"id":"2601.21281","title":"EGAM: Extended Graph Attention Model for Solving Routing Problems","created":"2026-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2602.03940","title":"Autonomous AI Agents for Real-Time Affordable Housing Site Selection: Multi-Objective Reinforcement Learning Under Regulatory Constraints","created":"2026-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2602.19538","title":"Cost-Aware Diffusion Active Search","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.06777","title":"HGT-Scheduler: Deep Reinforcement Learning for the Job Shop Scheduling Problem via Heterogeneous Graph Transformers","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":"2603.26264","title":"Topology-Aware Graph Reinforcement Learning for Energy Storage Systems Optimal Dispatch in Distribution Networks","created":"2026-03-27","cited_by_count":0,"area":"deeprl"},{"id":"2605.13638","title":"CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem","created":"2026-05-13","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":"2605.18437","title":"Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.05208","title":"Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks","created":"2026-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2606.06353","title":"Maximising the Set-Piece Return: Optimising Football Corner Tactics with Graph Reinforcement Learning","created":"2026-06-04","cited_by_count":0,"area":"deeprl"},{"id":"2606.18812","title":"Reinforcement Learning Foundation Models Should Already Be A Thing","created":"2026-06-17","cited_by_count":0,"area":"deeprl"},{"id":"2606.22922","title":"Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra","created":"2026-06-22","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":"2607.14008","title":"Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points","created":"2026-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2608.11498","title":"Language-Structured Relational Q-Learning for Threat-Aware Control in Safety-Critical Driving","created":"2026-08-11","cited_by_count":0,"area":"deeprl"},{"id":"2608.15929","title":"Unified Pedestrian Path Prediction Using Inverse Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2609.14952","title":"Cloud Workflow Scheduling Based on Graph Attention-Driven Hierarchical Reinforcement Learning","created":"2026-09-14","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"}],"next_cursor":null}