Co-Optimization of Environment and Policies for Decentralized Multi-Agent Navigation

arXiv:2403.14583v1 Announce Type: cross
Abstract: This work views the multi-agent system and its surrounding environment as a co-evolving system, where the behavior of one affects the other. The goal is to take both agent actions and environment configurations as decision variables, and optimize these two components in a coordinated manner to improve some measure of interest. Towards this end, we consider the problem of decentralized multi-agent navigation in cluttered environments. By introducing two sub-objectives of multi-agent navigation and environment optimization, …

abstract agent arxiv behavior components cs.lg cs.ma cs.ro decentralized decision environment multi-agent navigation optimization type variables work