Perolat, J;
Leibo, JZ;
Zambaldi, V;
Beattie, C;
Tuyls, K;
Graepel, T;
(2017)
A multi-agent reinforcement learning model of common-pool resource appropriation.
In: Guyon, I and Luxburg, UV and Bengio, S and Wallach, H and Fergus, R and Vishwanathan, S and Garnett, R, (eds.)
Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017).
Neural Information Processing Systems (NIPS)
Preview |
Text
GraepelVor6955-Graepel_a-multi-agent-reinforcement-learning-model-of-common-pool-resource-appropriation.pdf - Published Version Download (883kB) | Preview |
Abstract
Humanity faces numerous problems of common-pool resource appropriation. This class of multi-agent social dilemma includes the problems of ensuring sustainable use of fresh water, common fisheries, grazing pastures, and irrigation systems. Abstract models of common-pool resource appropriation based on non-cooperative game theory predict that self-interested agents will generally fail to find socially positive equilibria—a phenomenon called the tragedy of the commons. However, in reality, human societies are sometimes able to discover and implement stable cooperative solutions. Decades of behavioral game theory research have sought to uncover aspects of human behavior that make this possible. Most of that work was based on laboratory experiments where participants only make a single choice: how much to appropriate. Recognizing the importance of spatial and temporal resource dynamics, a recent trend has been toward experiments in more complex real-time video game like environments. However, standard methods of noncooperative game theory can no longer be used to generate predictions for this case. Here we show that deep reinforcement learning can be used instead. To that end, we study the emergent behavior of groups of independently learning agents in a partially observed Markov game modeling common-pool resource appropriation. Our experiments highlight the importance of trial-and-error learning in commonpool resource appropriation and shed light on the relationship between exclusion, sustainability, and inequality.
| Type: | Proceedings paper |
|---|---|
| Title: | A multi-agent reinforcement learning model of common-pool resource appropriation |
| Event: | 31st Conference on Neural Information Processing Systems (NIPS), 4-9 Dec 2017, Long Beach, CA, USA |
| Location: | Long Beach, CA |
| Dates: | 2017 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://papers.nips.cc/paper/6955-a-multi-agent-re... |
| Language: | English |
| Additional information: | This version is the version of the record. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices 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/10069052 |
Archive Staff Only
 |
View Item |
