{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:32:58Z","timestamp":1780500778925,"version":"3.54.1"},"reference-count":31,"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\/iros51168.2021.9636349","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"4583-4588","source":"Crossref","is-referenced-by-count":13,"title":["Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation"],"prefix":"10.1109","author":[{"given":"Enrico","family":"Marchesini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Farinelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"AAAI"},{"key":"ref30","article-title":"A hitchhiker's guide to statistical comparisons of rl algorithms","author":"colas","year":"2019"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66412-1_17"},{"key":"ref13","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"ICLRE"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining improvements in drl","author":"hessel","year":"2018","journal-title":"AAAI"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref16","article-title":"Virtual-to-real drl: Continuous control of mobile robots for mapless navigation","author":"tai","year":"2017","journal-title":"IROS"},{"key":"ref17","article-title":"Formal verification of neural networks for safety-critical tasks in deep reinforcement learning","author":"corsi","year":"2021","journal-title":"UAI"},{"key":"ref18","article-title":"Genetic soft updates for policy evolution in deep reinforcement learning","author":"marchesini","year":"2021","journal-title":"ICLRE"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196739"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500556"},{"key":"ref4","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2018","journal-title":"AAMAS"},{"key":"ref27","article-title":"Hypernetworks","author":"ha","year":"2017","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"ref6","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"ICML"},{"key":"ref29","article-title":"Unity: A platform for intelligent agents","author":"juliani","year":"2018","journal-title":"CoRR"},{"key":"ref5","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NIPS"},{"key":"ref8","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2017"},{"key":"ref7","article-title":"QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73424-6_2"},{"key":"ref9","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2426"},{"key":"ref20","article-title":"Genetic deep reinforcement learning for mapless navigation","author":"marchesini","year":"2020","journal-title":"AAMAS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11798","article-title":"Action branching architectures for deep reinforcement learning","author":"tavakoli","year":"2018","journal-title":"AAAI"},{"key":"ref24","article-title":"Reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"CoRR"},{"key":"ref23","article-title":"Q-learning in enormous action spaces via amortized approximate maximization","author":"wiele","year":"2018","journal-title":"NeurIPS workshop"},{"key":"ref26","article-title":"MAVEN: multi-agent variational exploration","author":"mahajan","year":"2019","journal-title":"NeuIPS"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"AAAI"}],"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\/09636349.pdf?arnumber=9636349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T22:41:03Z","timestamp":1674081663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636349","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}