{"ID":2851474,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19199","arxiv_id":"2510.19199","title":"A Communication-Efficient Decentralized Actor-Critic Algorithm","abstract":"In this paper, we study the problem of reinforcement learning in multi-agent systems where communication among agents is limited. We develop a decentralized actor-critic learning framework in which each agent performs several local updates of its policy and value function, where the latter is approximated by a multi-layer neural network, before exchanging information with its neighbors. This local training strategy substantially reduces the communication burden while maintaining coordination across the network. We establish finite-time convergence analysis for the algorithm under Markov-sampling. Specifically, to attain the $\\varepsilon$-accurate stationary point, the sample complexity is of order $\\mathcal{O}(\\varepsilon^{-3})$ and the communication complexity is of order $\\mathcal{O}(\\varepsilon^{-1}τ^{-1})$, where tau denotes the number of local training steps. We also show how the final error bound depends on the neural network's approximation quality. Numerical experiments in a cooperative control setting illustrate and validate the theoretical findings.","short_abstract":"In this paper, we study the problem of reinforcement learning in multi-agent systems where communication among agents is limited. We develop a decentralized actor-critic learning framework in which each agent performs several local updates of its policy and value function, where the latter is approximated by a multi-la...","url_abs":"https://arxiv.org/abs/2510.19199","url_pdf":"https://arxiv.org/pdf/2510.19199v1","authors":"[\"Xiaoxing Ren\",\"Nicola Bastianello\",\"Thomas Parisini\",\"Andreas A. Malikopoulos\"]","published":"2025-10-22T03:15:52Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"math.OC\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}