DePAint: A Decentralized Safe Multi-Agent Reinforcement Learning Algorithm considering Peak and Average Constraints

arXiv:2310.14348v2 Announce Type: replace-cross
Abstract: The domain of safe multi-agent reinforcement learning (MARL), despite its potential applications in areas ranging from drone delivery and vehicle automation to the development of zero-energy communities, remains relatively unexplored. The primary challenge involves training agents to learn optimal policies that maximize rewards while adhering to stringent safety constraints, all without the oversight of a central controller. These constraints are critical in a wide array of applications. Moreover, ensuring the privacy of sensitive information in …

abstract agent agents algorithm applications arxiv automation challenge communities constraints cs.ma decentralized delivery development domain drone energy learn multi-agent peak policies reinforcement reinforcement learning safe stat.ml training type