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


  • Dominik Linzner TU Darmstadt
  • Heinz Koeppl TU Darmstadt




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.




How to Cite

Linzner, D., & Koeppl, H. (2020). A Variational Perturbative Approach to Planning in Graph-Based Markov Decision Processes. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7203-7210. https://doi.org/10.1609/aaai.v34i05.6210



AAAI Technical Track: Multiagent Systems