Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances. The use of learning-based methods in multi-robot planning holds great promise as it enables us to offload the online computational burden of expensive, yet optimal solvers, to an offline learning procedure. Simply put, the idea is to train a policy to copy an optimal pattern generated by a small-scale system, and then transfer that policy to much larger systems, in the hope that the learned strategy scales, while maintaining near-optimal performance. Yet, a number of issues impede us from leveraging this idea to its full potential. This blue-sky paper elaborates some of the key challenges that remain.
In multi-agent reinforcement learning, the use of a global objective is a powerful tool for incentivising cooperation. Unfortunately, it is not sample-efficient to train individual agents with a global reward, because it does not necessarily correlate with an agent's individual actions. This problem can be solved by factorising the global value function into local value functions. Early work in this domain performed factorisation by conditioning local value functions purely on local information. Recently, it has been shown that providing both local information and an encoding of the global state can promote cooperative behaviour. In this paper we propose QGNN, the first value factorisation method to use a graph neural network (GNN) based model. The multi-layer message passing architecture of QGNN provides more representational complexity than models in prior work, allowing it to produce a more effective factorisation. QGNN also introduces a permutation invariant mixer which is able to match the performance of other methods, even with significantly fewer parameters. We evaluate our method against several baselines, including QMIX-Att, GraphMIX, QMIX, VDN, and hybrid architectures. Our experiments include Starcraft, the standard benchmark for credit assignment; Estimate Game, a custom environment that explicitly models interagent dependencies; and Coalition Structure Generation, a foundational problem with real-world applications. The results show that QGNN outperforms state-ofthe-art value factorisation baselines consistently.Preprint. Under review.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.