{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:27:51Z","timestamp":1775143671666,"version":"3.50.1"},"reference-count":22,"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\/iros51168.2021.9636193","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T15:45:38Z","timestamp":1639669538000},"page":"1859-1864","source":"Crossref","is-referenced-by-count":22,"title":["Cooperative Assistance in Robotic Surgery through Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Paul Maria","family":"Scheikl","sequence":"first","affiliation":[]},{"given":"Balazs","family":"Gyenes","sequence":"additional","affiliation":[]},{"given":"Tornike","family":"Davitashvili","sequence":"additional","affiliation":[]},{"given":"Rayan","family":"Younis","sequence":"additional","affiliation":[]},{"given":"Andre","family":"Schulze","sequence":"additional","affiliation":[]},{"given":"Beat P.","family":"Muller-Stich","sequence":"additional","affiliation":[]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Wagner","sequence":"additional","affiliation":[]},{"given":"Franziska","family":"Mathis-Ullrich","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"OpenAI Five","year":"2018"},{"key":"ref11","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref12","article-title":"Dynamic programming for partially observable stochastic games","author":"hansen","year":"2004","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/8415_2012_125"},{"key":"ref14","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref15","article-title":"rlpyt: A research code base for deep reinforcement learning in pytorch","author":"stooke","year":"2019"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref17","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/bjs.7115"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000909"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794159"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref5","article-title":"Open-sourced reinforcement learning environments for surgical robotics","author":"richter","year":"2019","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2980158"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2019.8836924"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-020-02194-z"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0b013e3181e6239e"},{"key":"ref9","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"2019"},{"key":"ref20","article-title":"Counterfactual multi-agent policy gradients","volume":"32","author":"foerster","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref22","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2020"},{"key":"ref21","article-title":"Transfer learning from synthetic to real images using variational autoencoders for robotic applications","author":"inoue","year":"2017"}],"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\/09636193.pdf?arnumber=9636193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:54:46Z","timestamp":1652187286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636193","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}