UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Adaptive Mechanism Design: Learning to Promote Cooperation

Baumann, T; Graepel, T; Shawe-Taylor, J; (2020) Adaptive Mechanism Design: Learning to Promote Cooperation. In: Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN). IEEE: Glasgow, UK. Green open access

[thumbnail of Adaptive_Mechanism_Design__IJCNN_submission.pdf]
Preview
Text
Adaptive_Mechanism_Design__IJCNN_submission.pdf - Accepted version

Download (403kB) | Preview

Abstract

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the problem of how an external agent can promote cooperation between artificial learners by distributing additional rewards and punishments based on observing the learners' actions. We propose a rule for automatically learning how to create the right incentives by considering the players' anticipated parameter updates. Using this learning rule leads to cooperation with high social welfare in matrix games in which the agents would otherwise learn to defect with high probability. We show that the resulting cooperative outcome is stable in certain games even if the planning agent is turned off after a given number of episodes, while other games require ongoing intervention to maintain mutual cooperation. However, even in the latter case, the amount of necessary additional incentives decreases over time.

Type: Proceedings paper
Title: Adaptive Mechanism Design: Learning to Promote Cooperation
Event: 2020 International Joint Conference on Neural Networks (IJCNN)
ISBN-13: 978-1-7281-6926-2
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/IJCNN48605.2020.9207690
Publisher version: https://doi.org/10.1109/IJCNN48605.2020.9207690
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Games, Planning, Markov processes, Learning (artificial intelligence), Symmetric matrices, Gradient methods, Task analysis
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10116156
Downloads since deposit
35Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item