Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Multiagent reinforcement learning methods to resolve demand capacity balance problems

Spatharis Christos, Kravaris Theocharis, Vouros, George A, Blekas Konstantinos D., Chalkiadakis Georgios, García José Manuel Cordero, Fernandez Esther Calvo

Full record


URI: http://purl.tuc.gr/dl/dias/491D12EE-D6EB-4D31-B04E-6A25CE948AD5
Year 2018
Type of Item Conference Full Paper
License
Details
Bibliographic Citation C. Spatharis, T. Kravaris, G. A. Vouros, K. Blekas, G. Chalkiadakis, J.M.C. Garcia and E.C. Fernandez, "Multiagent reinforcement learning methods to resolve demand capacity balance problems," in 10th Hellenic Conference on Artificial Intelligence, 2018. doi: 10.1145/3200947.3201010 https://doi.org/10.1145/3200947.3201010
Appears in Collections

Summary

In this article, we explore the computation of joint policies for autonomous agents to resolve congestions problems in the air traffic management (ATM) domain. Agents, representing flights, have limited information about others’ payoffs and preferences, and need to coordinate to achieve their tasks while adhering to operational constraints. We formalize the problem as a multiagent Markov decision process (MDP) towards deciding flight delays to resolve demand and capacity balance (DCB) problems in ATM. To this end, we present multiagent reinforcement learning methods that allow agents to interact and form own policies in coordination with others. Experimental study on real-world cases, confirms the effectiveness of our approach in resolving the demand-capacity balance problem.

Services

Statistics