{"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/maintaining-cooperation-in-complex-social","title":"Maintaining cooperation in complex social dilemmas using deep reinforcement learning","arxiv_id":"1707.01068","date":"2017-07-04","proceeding":"ICLR 2018 1","authors":["Adam Lerer","Alexander Peysakhovich"],"abstract":"Social dilemmas are situations where individuals face a temptation to\nincrease their payoffs at a cost to total welfare. Building artificially\nintelligent agents that achieve good outcomes in these situations is important\nbecause many real world interactions include a tension between selfish\ninterests and the welfare of others. We show how to modify modern reinforcement\nlearning methods to construct agents that act in ways that are simple to\nunderstand, nice (begin by cooperating), provokable (try to avoid being\nexploited), and forgiving (try to return to mutual cooperation). We show both\ntheoretically and experimentally that such agents can maintain cooperation in\nMarkov social dilemmas. Our construction does not require training methods\nbeyond a modification of self-play, thus if an environment is such that good\nstrategies can be constructed in the zero-sum case (eg. Atari) then we can\nconstruct agents that solve social dilemmas in this environment.","url_abs":"http://arxiv.org/abs/1707.01068v4","url_pdf":"http://arxiv.org/pdf/1707.01068v4.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":"maintaining-cooperation-in-complex-social","repo_url":"https://github.com/longtermrisk/marltoolbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"affine-coupling","method_name":"Affine Coupling"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.01068","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}