Open Ad Hoc Teamwork with Cooperative Game Theory

arXiv:2402.15259v1 Announce Type: cross
Abstract: Ad hoc teamwork poses a challenging problem, requiring the design of an agent to collaborate with teammates without prior coordination or joint training. Open ad hoc teamwork further complicates this challenge by considering environments with a changing number of teammates, referred to as open teams. The state-of-the-art solution to this problem is graph-based policy learning (GPL), leveraging the generalizability of graph neural networks to handle an unrestricted number of agents and effectively address open teams. …

abstract agent art arxiv challenge cs.lg cs.ma design environments game game theory prior state teams teamwork theory training type