Print Email Facebook Twitter Safe Multi-agent Learning via Trapping Regions Title Safe Multi-agent Learning via Trapping Regions Author Czechowski, A.T. (TU Delft Interactive Intelligence) Oliehoek, F.A. (TU Delft Interactive Intelligence) Contributor Elkind, Edith (editor) Date 2023 Abstract One of the main challenges of multi-agent learning lies in establishing convergence of the algorithms, as, in general, a collection of individual, self-serving agents is not guaranteed to converge with their joint policy, when learning concurrently. This is in stark contrast to most single-agent environments, and sets a prohibitive barrier for deployment in practical applications, as it induces uncertainty in long term behavior of the system. In this work, we apply the concept of trapping regions, known from qualitative theory of dynamical systems, to create safety sets in the joint strategy space for decentralized learning. We propose a binary partitioning algorithm for verification that candidate sets form trapping regions in systems with known learning dynamics, and a heuristic sampling algorithm for scenarios where learning dynamics are not known. We demonstrate the applications to a regularized version of Dirac Generative Adversarial Network, a four-intersection traffic control scenario run in a state of the art open-source microscopic traffic simulator SUMO, and a mathematical model of economic competition. To reference this document use: http://resolver.tudelft.nl/uuid:c4839d9c-b915-4598-8e01-fd1b35c3f08a Publisher International Joint Conferences on Artificial Intelligence (IJCAI) ISBN 9781956792034 Source Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023 Event 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023, 2023-08-19 → 2023-08-25, Macao, China Series IJCAI International Joint Conference on Artificial Intelligence, 1045-0823, 2023-August Part of collection Institutional Repository Document type conference paper Rights © 2023 A.T. Czechowski, F.A. Oliehoek Files PDF 0010.pdf 427.43 KB Close viewer /islandora/object/uuid:c4839d9c-b915-4598-8e01-fd1b35c3f08a/datastream/OBJ/view