Incentive-based MARL Approach for Commons Dilemmas in Property-based Environments : Extended Abstract

Pelcner, Lukasz and do Carmo Alves, Matheus Aparecido and Soriano Marcolino, Leandro and Harrison, Paula and Atkinson, Peter (2023) Incentive-based MARL Approach for Commons Dilemmas in Property-based Environments : Extended Abstract. In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems :. IFAAMAS, NZL. (In Press)

[thumbnail of pelcner2024incentive]
Text (pelcner2024incentive)
AAMAS_24_extended_abstract.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (733kB)

Abstract

We propose ORAA, a novel online incentive algorithm that guides agents in a property-based MARL domain to act sustainably with a common pool of resources. ORAA uses 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 MARL scenario and its incentivisation dynamics. We show significant improvement in the incentives’ cost-efficiency when using learned models that approximate the behaviour of each agent instead of simulating their true models.

Item Type:
Contribution in Book/Report/Proceedings
Uncontrolled Keywords:
Research Output Funding/no_not_funded
Subjects:
?? reinforcement learningmulti-agents systemproperty-based environmentcommon-pool resourcesno - not fundedno ??
ID Code:
215041
Deposited By:
Deposited On:
23 Apr 2024 13:05
Refereed?:
Yes
Published?:
In Press
Last Modified:
16 Oct 2024 23:27