Hughes, Edward, Leibo, Joel Z, Phillips, Matthew, Tuyls, Karl, Duenez-Guzman, Edgar, Castaneda, Antonio Garcia, Dunning, Iain, Zhu, Tina, McKee, Kevin, Koster, Raphael et al (show 2 more authors)
(2018)
Inequity aversion improves cooperation in intertemporal social dilemmas.
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 31.
pp. 3326-3336.
![[img]](https://livrepository.liverpool.ac.uk/style/images/fileicons/text.png) |
Text
1803.08884v3.pdf - Submitted version Download (2MB) |
Abstract
Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas. Models based on behavioral economics are only able to explain this phenomenon for unrealistic stateless matrix games. Recently, multi-agent reinforcement learning has been applied to generalize social dilemma problems to temporally and spatially extended Markov games. However, this has not yet generated an agent that learns to cooperate in social dilemmas as humans do. A key insight is that many, but not all, human individuals have inequity averse social preferences. This promotes a particular resolution of the matrix game social dilemma wherein inequity-averse individuals are personally pro-social and punish defectors. Here we extend this idea to Markov games and show that it promotes cooperation in several types of sequential social dilemma, via a profitable interaction with policy learnability. In particular, we find that inequity aversion improves temporal credit assignment for the important class of intertemporal social dilemmas. These results help explain how large-scale cooperation may emerge and persist.
| Item Type: | Article |
|---|---|
| Additional Information: | 15 pages, 8 figures |
| Uncontrolled Keywords: | cs.NE, cs.NE, cs.AI, cs.GT, cs.MA, q-bio.PE |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 10 Dec 2018 15:16 |
| Last Modified: | 19 Jan 2023 01:09 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3029648 |
Share
Share
