{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/inequity-aversion-improves-cooperation-in","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","arxiv_id":"1803.08884","date":"2018-03-23","proceeding":"NeurIPS 2018 12","authors":["Edward Hughes","Joel Z. Leibo","Matthew G. Phillips","Karl Tuyls","Edgar A. Duéñez-Guzmán","Antonio García Castañeda","Iain Dunning","Tina Zhu","Kevin R. McKee","Raphael Koster","Heather Roff","Thore Graepel"],"abstract":"Groups of humans are often able to find ways to cooperate with one another in\ncomplex, temporally extended social dilemmas. Models based on behavioral\neconomics are only able to explain this phenomenon for unrealistic stateless\nmatrix games. Recently, multi-agent reinforcement learning has been applied to\ngeneralize social dilemma problems to temporally and spatially extended Markov\ngames. However, this has not yet generated an agent that learns to cooperate in\nsocial dilemmas as humans do. A key insight is that many, but not all, human\nindividuals have inequity averse social preferences. This promotes a particular\nresolution of the matrix game social dilemma wherein inequity-averse\nindividuals are personally pro-social and punish defectors. Here we extend this\nidea to Markov games and show that it promotes cooperation in several types of\nsequential social dilemma, via a profitable interaction with policy\nlearnability. In particular, we find that inequity aversion improves temporal\ncredit assignment for the important class of intertemporal social dilemmas.\nThese results help explain how large-scale cooperation may emerge and persist.","url_abs":"http://arxiv.org/abs/1803.08884v3","url_pdf":"http://arxiv.org/pdf/1803.08884v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"inequity-aversion-improves-cooperation-in","repo_url":"https://github.com/eugenevinitsky/sequential_social_dilemma_games","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"inequity-aversion-improves-cooperation-in","repo_url":"https://github.com/social-dilemma/multiagent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"inequity-aversion-improves-cooperation-in","repo_url":"https://github.com/vermashresth/sequential_social_dilemma_games","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.08884","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}