Decentralized MCTS via Learned Teammate Models

Conference Paper (2020)
Author(s)

Aleksander Czechowski (TU Delft - Interactive Intelligence)

F.A. Oliehoek (TU Delft - Interactive Intelligence)

Research Group
Interactive Intelligence
Copyright
© 2020 A.T. Czechowski, F.A. Oliehoek
DOI related publication
https://doi.org/10.24963/ijcai.2020/12
More Info
expand_more
Publication Year
2020
Language
English
Copyright
© 2020 A.T. Czechowski, F.A. Oliehoek
Research Group
Interactive Intelligence
Pages (from-to)
81-88
ISBN (electronic)
978-0-9992411-6-5
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Decentralized online planning can be an attractive paradigm for cooperative multi-agent systems, due to improved scalability and robustness. A key difficulty of such approach lies in making accurate predictions about the decisions of other agents. In this paper, we present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search, combined with models of teammates learned from previous episodic runs. By only allowing one agent to adapt its models at a time, under the assumption of ideal policy approximation, successive iterations of our method are guaranteed to improve joint policies, and eventually lead to convergence to a Nash equilibrium. We test the efficiency of the algorithm by performing experiments in several scenarios of the spatial task allocation environment introduced in [Claes et al., 2015]. We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators which exploit the spatial features of the problem, and that the proposed algorithm improves over the baseline planning performance for particularly challenging domain configurations.

Files

0012.pdf
(pdf | 0.458 Mb)
License info not available