{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T12:15:52Z","timestamp":1774959352985,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196684","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"10695-10701","source":"Crossref","is-referenced-by-count":22,"title":["Learning Multi-Robot Decentralized Macro-Action-Based Policies via a Centralized Q-Net"],"prefix":"10.1109","author":[{"given":"Yuchen","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua","family":"Hoffman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Amato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"CoRR"},{"key":"ref11","article-title":"Macro-action-based deep multi-agent reinforcement learning","author":"xiao","year":"2019","journal-title":"3nd Annual Conference on Robot Learning (CoRL)"},{"key":"ref12","article-title":"Planning with macro-actions in decentralized POMDPs","author":"amato","year":"2014","journal-title":"Proc Autonomous Agents and Multiagent Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11418"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Deep recurrent Q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (AAAI-SDMIA15)"},{"key":"ref17","first-page":"2613","article-title":"Double Q-learning","volume":"23","author":"hasselt","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016","journal-title":"Proc of the Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65340-2_11"},{"key":"ref4","article-title":"Fetch & freight : Standard platforms for service robot applications","author":"wise","year":"2016","journal-title":"Workshop on Autonomous Mobile Service Robots International Joint Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2017.8008500"},{"key":"ref6","first-page":"2681","article-title":"Deep de-centralized multi-task multi-agent reinforcement learning under partial observability","author":"omidsha ei","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2016.66"},{"key":"ref8","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref7","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"AAAI 2018-The Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref2","first-page":"33","article-title":"Optimization and coordinated autonomy in mobile fulfillment systems","author":"enright","year":"2011","journal-title":"Proceedings of the 9th AAAI Conference on Automated Action Planning for Autonomous Mobile Robots"},{"key":"ref9","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"ICML 2018 Proceedings of the Thirty-Fifth International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594239"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97310-4_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref24","article-title":"ROS: an open-source robot operating system","author":"quigley","year":"2009","journal-title":"ICRA Workshop on Open Source Software"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2015.2448951"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/MRA.2012.2205651","article-title":"The Open Motion Planning Library","volume":"19","author":"?ucan","year":"2012","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"ref25","article-title":"Openrave: A planning architecture for autonomous robotics","author":"diankov","year":"2008","journal-title":"Carnegie Mellon University Pittsburgh PA Tech Rep"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196684.pdf?arnumber=9196684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:14:34Z","timestamp":1656375274000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196684","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}