Incentive-Driven Multi-agent Reinforcement Learning Approach for Commons Dilemmas in Land-Use

Pelcner, Lukasz and do Carmo Alves, Matheus Aparecido and Soriano Marcolino, Leandro and Harrison, Paula and Atkinson, Peter (2024) Incentive-Driven Multi-agent Reinforcement Learning Approach for Commons Dilemmas in Land-Use. In: PRIMA 2024: Principles and Practice of Multi-Agent Systems: : 25th International Conference, Kyoto, Japan, November 18–24, 2024, Proceedings. Lecture Notes in Computer Science . Springer, Cham, pp. 284-289. ISBN 9783031773662

Text (pelcner2024incentive)
pelcner2024incentive.pdf - Accepted Version
Available under License Unspecified.
Download (568kB)

Abstract

We propose ORAA, a novel incentive-driven algorithm that guides agents in a property-based Multi-Agent Reinforcement Learning domain to act sustainably considering a common pool of resources in an online manner. ORAA implements our proposed P-MADDPG model to learn and make decisions over the decentralised agents. We test our solutions in our novel domain, the “Pollinators’ Game”, which simulates a property-based scenario and the incentivisation dynamics. We show significant improvement in the incentives’ cost-efficiency, reducing the budget spent while increasing the collection of rewards by individual agents. Besides that, our application shows better results when using learned (approximated) models instead of using and simulating the true models of each agent for planning, saving up to 50% of the available budget for incentivisation.