{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:23:11Z","timestamp":1762953791926,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341696","type":"proceedings-article","created":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T21:26:48Z","timestamp":1613165208000},"page":"5380-5386","source":"Crossref","is-referenced-by-count":2,"title":["Tensor Action Spaces for Multi-agent Robot Transfer Learning"],"prefix":"10.1109","author":[{"given":"Devin","family":"Schwab","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuela","family":"Veloso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Zero shot transfer learning for robot soccer","author":"schwab","year":"2018","journal-title":"AAMAS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","first-page":"3982","article-title":"Transfer learning for multiagent reinforcement learning systems","author":"da silva","year":"2016","journal-title":"IJCAI"},{"key":"ref13","first-page":"249","article-title":"Transfer learning in multi-agent reinforcement learning domains","author":"boutsioukis","year":"2011","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"article-title":"Transfer learning in multi-agent systems through parallel transfer","year":"2013","author":"taylor","key":"ref14"},{"key":"ref15","article-title":"Accelerating multi-agent reinforcement learning with dynamic co-learning","author":"garant","year":"2015","journal-title":"Technical Report Tech Rep"},{"key":"ref16","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref17","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref18","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2015","journal-title":"CoRR"},{"article-title":"Dueling network architectures for deep reinforcement learning","year":"2015","author":"wang","key":"ref19"},{"article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref4"},{"article-title":"Continuous control with deep reinforcement learning","year":"0","author":"lillicrap","key":"ref3"},{"article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","year":"2017","author":"silver","key":"ref6"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","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"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref1"},{"year":"2017","key":"ref9","article-title":"RoboCup"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967787"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341696.pdf?arnumber=9341696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T17:56:58Z","timestamp":1656439018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341696","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}