Multiagent reinforcement learning methods to resolve demand capacity balance problemsMultiagent reinforcement learning methods to resolve demand capacity balance problems Πλήρης Δημοσίευση σε Συνέδριο Conference Full Paper 2019-08-302018enIn 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.http://creativecommons.org/licenses/by/4.0/10th Hellenic Conference on Artificial IntelligenceProceedings of the 10th Hellenic Conference on Artificial Intelligence Spatharis Christos Kravaris Theocharis Vouros, George A Blekas Konstantinos D. Chalkiadakis Georgios Χαλκιαδακης Γεωργιος García José Manuel Cordero Fernandez Esther Calvo Association for Computing Machinery Air Traffic Management Congestion problems Demand Capacity Balance Multi-agent reinforcement learning