Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing

arXiv:2402.17666v1 Announce Type: new
Abstract: This paper introduces a Multi-Agent Deep Reinforcement Learning (MA-DRL) approach for routing in Low Earth Orbit Satellite Constellations (LSatCs). Each satellite is an independent decision-making agent with a partial knowledge of the environment, and supported by feedback received from the nearby agents. Building on our previous work that introduced a Q-routing solution, the contribution of this paper is to extend it to a deep learning framework able to quickly adapt to the network and traffic …

abstract agent agents arxiv building cs.lg decision distributed earth environment feedback independent knowledge low low earth orbit making multi-agent paper reinforcement reinforcement learning routing satellite the environment type work