Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition

arXiv:2302.04944v2 Announce Type: replace-cross
Abstract: Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The …

abstract agent agents arxiv challenges cs.ai cs.lg cs.ma multi-agent policy reinforcement reinforcement learning search space tasks team teamwork training type via