A Variational Perturbative Approach to Planning in Graph-based Markov Decision Processes
This addresses the problem of coordinating multiple agents on graphs for researchers in multi-agent systems, but it appears incremental as it builds on existing planning via inference methods.
The paper tackles multi-agent planning on graphs using a variational perturbative approach, showing that their method outperforms state-of-the-art methods in cases with non-local cost functions and significantly improves synchronization tasks.
Coordinating multiple interacting agents to achieve a common goal is a difficult task with huge applicability. This problem remains hard to solve, even when limiting interactions to be mediated via a static interaction-graph. We present a novel approximate solution method for multi-agent Markov decision problems on graphs, based on variational perturbation theory. We adopt the strategy of planning via inference, which has been explored in various prior works. We employ a non-trivial extension of a novel high-order variational method that allows for approximate inference in large networks and has been shown to surpass the accuracy of existing variational methods. To compare our method to two state-of-the-art methods for multi-agent planning on graphs, we apply the method different standard GMDP problems. We show that in cases, where the goal is encoded as a non-local cost function, our method performs well, while state-of-the-art methods approach the performance of random guess. In a final experiment, we demonstrate that our method brings significant improvement for synchronization tasks.