{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:28:25Z","timestamp":1780054105963,"version":"3.54.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9635836","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"5635-5640","source":"Crossref","is-referenced-by-count":19,"title":["MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Willemsen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Coppola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guido C.H.E.","family":"de Croon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep State-Space Models¨ in Multi-Agent Systems","author":"indarjo","year":"0","journal-title":"Master’s thesis Leiden University"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11492","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref13","article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","author":"de witt","year":"2020"},{"key":"ref14","article-title":"Regularization for deep? learning: A taxonomy","author":"kuka?ka","year":"2017"},{"key":"ref15","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70 ser ICML’17"},{"key":"ref16","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref4","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/978-3-540-74089-6_3","article-title":"Swarm Robotics","author":"sahin","year":"2008","journal-title":"Swarm Intelligence"},{"key":"ref6","article-title":"Probabilistic View of Multi-agent Reinforcement Learning: A Unified Approach","author":"gupta","year":"2019"},{"key":"ref5","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","author":"chua","year":"2018"},{"key":"ref7","article-title":"Benchmarking model-based reinforcement learning","author":"wang","year":"2019"},{"key":"ref2","first-page":"12498","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","article-title":"Multi-Agent Reinforcement Learning with Multi-Step Generative Models","author":"krupnik","year":"2019"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09635836.pdf?arnumber=9635836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:38:58Z","timestamp":1674081538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9635836\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9635836","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}