{"total":32,"rows":[{"id":"2112.09559","title":"ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms","created":"2021-12-17","cited_by_count":35,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2110.02128","title":"NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2109.05536","title":"Link Scheduling using Graph Neural Networks","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2209.14171","title":"Programmable and Customized Intelligence for Traffic Steering in 5G Networks Using Open RAN Architectures","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2110.14541","title":"Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks","created":"2021-10-24","cited_by_count":8,"area":null},{"id":"2106.09274","title":"Cooperative Multi-Agent Reinforcement Learning Based Distributed Dynamic Spectrum Access in Cognitive Radio Networks","created":"2021-06-17","cited_by_count":7,"area":null},{"id":"2101.01336","title":"Joint Deep Reinforcement Learning and Unfolding: Beam Selection and Precoding for mmWave Multiuser MIMO with Lens Arrays","created":"2021-01-05","cited_by_count":6,"area":null},{"id":"2303.15544","title":"Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach","created":"2023-03-27","cited_by_count":6,"area":null},{"id":"2105.04077","title":"Dynamic Multichannel Access via Multi-agent Reinforcement Learning: Throughput and Fairness Guarantees","created":"2021-05-10","cited_by_count":4,"area":null},{"id":"2103.03745","title":"Can You Fix My Neural Network? Real-Time Adaptive Waveform Synthesis for Resilient Wireless Signal Classification","created":"2021-03-05","cited_by_count":3,"area":null},{"id":"2201.08477","title":"DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning","created":"2022-01-20","cited_by_count":2,"area":null},{"id":"2104.02059","title":"Distributed Deep Reinforcement Learning for Collaborative Spectrum Sharing","created":"2021-04-06","cited_by_count":1,"area":null},{"id":"2105.05817","title":"Adversarial Reinforcement Learning in Dynamic Channel Access and Power Control","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2108.02551","title":"Ensemble Consensus-based Representation Deep Reinforcement Learning for Hybrid FSO/RF Communication Systems","created":"2021-08-05","cited_by_count":1,"area":null},{"id":"2201.07090","title":"A Machine Learning Based Algorithm for Joint Improvement of Power Control, link adaptation, and Capacity in Beyond 5G Communication systems","created":"2022-01-08","cited_by_count":1,"area":null},{"id":"2210.01423","title":"Using Deep Reinforcement Learning for mmWave Real-Time Scheduling","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2302.04519","title":"RayNet: A Simulation Platform for Developing Reinforcement Learning-Driven Network Protocols","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2308.05036","title":"Collaborative Wideband Spectrum Sensing and Scheduling for Networked UAVs in UTM Systems","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2406.01727","title":"Federated Learning-based Collaborative Wideband Spectrum Sensing and Scheduling for UAVs in UTM Systems","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2408.09882","title":"GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits","created":"2024-08-19","cited_by_count":1,"area":null},{"id":"2503.15172","title":"Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2601.04511","title":"Multiagent Reinforcement Learning with Neighbor Action Estimation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2610.04345","title":"System One Models for Wireless Decision-Making:Applications and Performance Evaluation","created":"2026-10-03","cited_by_count":1,"area":null},{"id":"2106.11595","title":"Reinforcement Learning for Physical Layer Communications","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2107.07049","title":"Learning-based Spectrum Sensing and Access in Cognitive Radios via Approximate POMDPs","created":"2021-07-14","cited_by_count":0,"area":null},{"id":"2201.09075","title":"Dynamic Channel Access via Meta-Reinforcement Learning","created":"2021-12-24","cited_by_count":0,"area":null},{"id":"2310.08660","title":"Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2406.07848","title":"Multi-agent Reinforcement Learning with Deep Networks for Diverse Q-Vectors","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2608.22992","title":"Channel-Token Attention for Reliable Dynamic Spectrum Access under Bursty Primary-User Traffic","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.04802","title":"Multi-Agent Spectrum Sharing","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}