Preprint Open Access

A Variational Perturbative Approach to Planning in Graph-Based Markov Decision Processes

Linzner, Dominik; Koeppl, Heinz

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.

Files (577.8 kB)
Name Size
AAAI-LinznerD.4021.pdf
md5:a8344c21a7790a4598a4d49b3661b079
577.8 kB Download
13
12
views
downloads
Views 13
Downloads 12
Data volume 6.9 MB
Unique views 13
Unique downloads 12

Share

Cite as