{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T12:03:53Z","timestamp":1757592233387,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533333","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T17:27:41Z","timestamp":1632158861000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Distributed Emergent Agreements with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kyrill","family":"Schmid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Muller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lenz","family":"Belzner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Tochtermann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"Linhoff-Popien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3643","article-title":"A multi-agent reinforcement learning model of common-pool resource appropriation","author":"perolat","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Towards cooperation in sequential prisoner's dilemmas: a deep multiagent reinforcement learning approach","author":"wang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"3326","article-title":"Inequity aversion improves cooperation in intertemporal social dilemmas","author":"hughes","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"122","article-title":"Learning with Opponent-Learning Awareness","author":"foerster","year":"0","journal-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems IFAAMAS"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref19","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref4","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","author":"sunehag","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref5","first-page":"2137","article-title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Open problems in cooperative ai","author":"dafoe","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"464","article-title":"Multi-Agent Reinforcement Learning in Sequential Social Dilemmas","author":"leibo","year":"0","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems IFAAMAS"},{"key":"ref2","article-title":"Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref9","first-page":"1090","article-title":"Bayesian reinforcement learning for coalition formation under uncertainty","author":"chalkiadakis","year":"0","journal-title":"Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems- Volume 3"},{"key":"ref20","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"clevert","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"6382","article-title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533333.pdf?arnumber=9533333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:46:01Z","timestamp":1652183161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533333","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}