{"total":54,"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":"2305.10697","title":"The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond","created":"2023-05-18","cited_by_count":36,"area":null},{"id":"2110.14153","title":"Differentially Private Federated Bayesian Optimization with Distributed Exploration","created":"2021-10-27","cited_by_count":32,"area":null},{"id":"2401.15273","title":"Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning","created":"2024-01-27","cited_by_count":31,"area":"deeprl"},{"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":"2210.06850","title":"Sample-Then-Optimize Batch Neural Thompson Sampling","created":"2022-10-13","cited_by_count":25,"area":null},{"id":"2205.14309","title":"Federated Neural Bandits","created":"2022-05-28","cited_by_count":17,"area":null},{"id":"2206.00165","title":"Byzantine-Robust Online and Offline Distributed Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":null},{"id":"2206.05581","title":"Federated Offline Reinforcement Learning","created":"2022-06-11","cited_by_count":13,"area":"offlinerl"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2402.05876","title":"Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices","created":"2024-02-08","cited_by_count":11,"area":"offlinerl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"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":"2204.01155","title":"Byzantine-Robust Federated Linear Bandits","created":"2022-04-03","cited_by_count":8,"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":"2405.19499","title":"Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments","created":"2024-05-29","cited_by_count":8,"area":"deeprl"},{"id":"2502.08123","title":"Provably Robust Federated Reinforcement Learning","created":"2025-02-12","cited_by_count":8,"area":"deeprl"},{"id":"2306.15968","title":"Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning","created":"2023-06-28","cited_by_count":7,"area":"driving"},{"id":"2301.11135","title":"FedHQL: Federated Heterogeneous Q-Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2303.02725","title":"Local Environment Poisoning Attacks on Federated Reinforcement Learning","created":"2023-03-05","cited_by_count":6,"area":null},{"id":"2403.09940","title":"Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2404.10635","title":"Compressed Federated Reinforcement Learning with a Generative Model","created":"2024-03-26","cited_by_count":6,"area":"deeprl"},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2411.15014","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations","created":"2024-11-22","cited_by_count":4,"area":"deeprl"},{"id":"2502.02859","title":"Gap-Dependent Bounds for Federated $Q$-learning","created":"2025-02-05","cited_by_count":4,"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":"2310.07320","title":"Byzantine-Resilient Decentralized Multi-Armed Bandits","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2403.13245","title":"Federated reinforcement learning for robot motion planning with zero-shot generalization","created":"2024-03-20","cited_by_count":3,"area":"deeprl"},{"id":"2409.12882","title":"On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attacks","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2401.03489","title":"Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence","created":"2024-01-07","cited_by_count":2,"area":"deeprl"},{"id":"2402.09729","title":"Federated Prompt-based Decision Transformer for Customized VR Services in Mobile Edge Computing System","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2403.20156","title":"CAESAR: Enhancing Federated RL in Heterogeneous MDPs through Convergence-Aware Sampling with Screening","created":"2024-03-29","cited_by_count":2,"area":"deeprl"},{"id":"2503.17454","title":"Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis","created":"2025-03-21","cited_by_count":2,"area":"deeprl"},{"id":"2504.11645","title":"Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling","created":"2025-04-15","cited_by_count":2,"area":"deeprl"},{"id":"2506.01261","title":"The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning","created":"2025-06-02","cited_by_count":2,"area":"deeprl"},{"id":"2506.04626","title":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2602.13320","title":"Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol","created":"2026-02-10","cited_by_count":2,"area":"agents"},{"id":"2209.10072","title":"On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2301.08015","title":"Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2405.17471","title":"Momentum-Based Federated Reinforcement Learning with Interaction and Communication Efficiency","created":"2024-05-24","cited_by_count":1,"area":"deeprl"},{"id":"2405.17474","title":"Federated Offline Policy Optimization with Dual Regularization","created":"2024-05-24","cited_by_count":1,"area":"offlinerl"},{"id":"2608.16971","title":"FedPref: Federated Preference Learning for Structured Radiology Report Extraction","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2304.12778","title":"Loss- and Reward-Weighting for Efficient Distributed Reinforcement Learning","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2412.14555","title":"Single-Loop Federated Actor-Critic across Heterogeneous Environments","created":"2024-12-19","cited_by_count":0,"area":"deeprl"},{"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":"2505.09959","title":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","created":"2025-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2605.29002","title":"FedQHD: Closed-Form Function-Space Federated Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2607.08137","title":"Securing Autonomous Vehicle Systems via Twin-Aware Federated Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"driving"},{"id":"2608.10499","title":"Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation","created":"2026-08-11","cited_by_count":0,"area":"deeprl"},{"id":"2609.18964","title":"FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning","created":"2026-07-22","cited_by_count":0,"area":"diffusion"},{"id":"2610.01195","title":"Federated Agent Optimization","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06918","title":"Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}