Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning

arXiv:2401.15273v2 Announce Type: replace
Abstract: Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, …

abstract agent agents analysis arxiv complexity cs.lg cs.sy eess.sy environment however information math.oc nothing paradigm performance policy reinforcement reinforcement learning sample tasks type