{"total":47,"rows":[{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2204.08125","title":"FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence","created":"2022-04-18","cited_by_count":29,"area":null},{"id":"2305.08104","title":"Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling","created":"2023-05-14","cited_by_count":15,"area":null},{"id":"2205.01423","title":"Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2210.13111","title":"Federated Learning and Meta Learning: Approaches, Applications, and Directions","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2301.00944","title":"Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning","created":"2023-01-03","cited_by_count":12,"area":null},{"id":"2307.11432","title":"An Analysis of Multi-Agent Reinforcement Learning for Decentralized Inventory Control Systems","created":"2023-07-21","cited_by_count":11,"area":null},{"id":"2311.00201","title":"Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning","created":"2023-11-01","cited_by_count":11,"area":null},{"id":"2403.02619","title":"Training Machine Learning models at the Edge: A Survey","created":"2024-03-05","cited_by_count":11,"area":null},{"id":"2305.10997","title":"Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2203.01198","title":"Linear Stochastic Bandits over a Bit-Constrained Channel","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2205.13697","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2306.05764","title":"Fair yet Asymptotically Equal Collaborative Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2302.11466","title":"Advancements in Federated Learning: Models, Methods, and Privacy","created":"2023-02-22","cited_by_count":7,"area":null},{"id":"2402.04114","title":"SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2111.12064","title":"Semantic-Aware Collaborative Deep Reinforcement Learning Over Wireless Cellular Networks","created":"2021-11-23","cited_by_count":6,"area":null},{"id":"2410.22908","title":"Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2503.09956","title":"DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2210.01452","title":"Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2212.02075","title":"Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks","created":"2022-12-05","cited_by_count":4,"area":null},{"id":"2210.08065","title":"Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2211.02296","title":"Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2302.04944","title":"Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2304.01525","title":"Online Learning with Adversaries: A Differential-Inclusion Analysis","created":"2023-04-04","cited_by_count":3,"area":null},{"id":"2305.10978","title":"Client Selection for Federated Policy Optimization with Environment Heterogeneity","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2306.02029","title":"Model-aided Federated Reinforcement Learning for Multi-UAV Trajectory Planning in IoT Networks","created":"2023-06-03","cited_by_count":3,"area":null},{"id":"2310.09858","title":"Federated Reinforcement Learning for Resource Allocation in V2X Networks","created":"2023-10-15","cited_by_count":3,"area":null},{"id":"2407.11069","title":"Combining Federated Learning and Control: A Survey","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2308.08792","title":"Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2512.17688","title":"Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2207.03484","title":"AVDDPG: Federated reinforcement learning applied to autonomous platoon control","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2210.06820","title":"Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2212.08973","title":"Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2302.02250","title":"Generalization of Deep Reinforcement Learning for Jammer-Resilient Frequency and Power Allocation","created":"2023-02-04","cited_by_count":1,"area":null},{"id":"2304.14720","title":"A Federated Reinforcement Learning Framework for Link Activation in Multi-link Wi-Fi Networks","created":"2023-04-28","cited_by_count":1,"area":null},{"id":"2305.00780","title":"AI-based Radio and Computing Resource Allocation and Path Planning in NOMA NTNs: AoI Minimization under CSI Uncertainty","created":"2023-05-01","cited_by_count":1,"area":null},{"id":"2407.02342","title":"Optimizing Age of Information in Vehicular Edge Computing with Federated Graph Neural Network Multi-Agent Reinforcement Learning","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2502.06044","title":"Differentially Private Hyperparameter Tuning using Local Bayesian Optimization","created":"2025-02-09","cited_by_count":1,"area":null},{"id":"2112.05812","title":"Edge-Compatible Reinforcement Learning for Recommendations","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2310.16592","title":"Over-the-air Federated Policy Gradient","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2311.01749","title":"Epidemic Decision-making System Based Federated Reinforcement Learning","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2311.12264","title":"Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2501.10938","title":"Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2506.07980","title":"Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2509.10163","title":"Federated Multi-Agent Reinforcement Learning for Privacy-Preserving and Energy-Aware Resource Management in 6G Edge Networks","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2604.05088","title":"Scalar Federated Learning for Linear Quadratic Regulator","created":"2026-04-06","cited_by_count":0,"area":null}],"next_cursor":null}