{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T18:40:07Z","timestamp":1752000007068,"version":"3.41.2"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8463215","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"7688-7695","source":"Crossref","is-referenced-by-count":11,"title":["Learning Robust Policies for Object Manipulation with Robot Swarms"],"prefix":"10.1109","author":[{"given":"Gregor H.W.","family":"Gebhardt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Daun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marius","family":"Schnaubelt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Multi-robot learning with particle swarm optimization","author":"pugh","year":"2006","journal-title":"Proceedings of the 3rd International Conference on Autonomous Agents and Multi-Agent Systems"},{"year":"2007","journal-title":"IEEE Congress on Evolutionary Computation","article-title":"Parallel learning in heterogeneous multi-robot swarms","key":"ref11"},{"year":"2010","author":"martel","journal-title":"Using a swarm of self-propelled natural microrobots in the form of flagellated bacteria to perform complex micro-assembly tasks","key":"ref12"},{"year":"2016","author":"shahrokhi","journal-title":"Object manipulation and position control using a swarm with global inputs","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Proceedings of the 24th AAAI Conference on Artificial Intelligence"},{"key":"ref15","article-title":"Least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proceedings of the 16th International Conference on Machine Learning"},{"key":"ref16","article-title":"Regularized least squares temporal difference learning with nested 12 and 11 penalization","author":"hoffman","year":"2011","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"year":"2017","author":"van hoof","journal-title":"Non-parametric policy search with limited information loss","key":"ref17"},{"key":"ref18","article-title":"Model-based contextual policy search for data-efficient generalization of robot skills","author":"kupcsik","year":"2015","journal-title":"Artificial Intelligence"},{"key":"ref19","article-title":"Sparse gaussian processes using pseudo-inputs","author":"snelson","year":"2005","journal-title":"Advances in Neural Information Processing Systems 18"},{"year":"2013","author":"bonnard","journal-title":"Chilitags 2 Robust fiducial markersfor augmented reality and robotics","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-75225-7_5","article-title":"A hilbert space embedding for distributions","author":"smola","year":"2007","journal-title":"Proc Int Conf Algorithmic Learn Theory"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1111\/1467-8659.00689"},{"key":"ref3","article-title":"Collective transport of complex objects by simple robots: Theory and experiments","author":"rubenstein","year":"2013","journal-title":"Proc 1st Int Conf Autonomous Agents and Multi-Agent Systems"},{"key":"ref6","article-title":"Learning to assemble objects with a robot swarm","author":"gebhardt","year":"2017","journal-title":"Proceedings of the Autonomous Agents and Multi Agents System Conference"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10269","article-title":"Model-free preference-based reinforcement learning","author":"wirth","year":"2016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref8","article-title":"A reinforcement learning system for swarm behaviors","author":"kuremoto","year":"2008","journal-title":"IEEE International Joint Conference on Neural Networks"},{"key":"ref7","article-title":"An actor-critic approach for learning cooperative behaviors of multiagent seesaw balancing problems","author":"kawakami","year":"2005","journal-title":"IEEE International Conference on Systems Man and Cybernetics"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.robot.2013.08.006"},{"key":"ref9","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1007\/978-3-540-30301-5_41"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1090\/S0002-9947-1950-0051437-7"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1177\/027836498600500106"},{"key":"ref21","article-title":"A formal basis for the heuristic determination of minimum cost paths","author":"hart","year":"0","journal-title":"IEEE Transactions on Systems Science and Cybernetics 1968"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2013.6696401","article-title":"Massive uniform manipulation: Controlling large populations of simple robots with a common input signal","author":"becker","year":"2013","journal-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref23","article-title":"Potential field methods and their inherent limitations for mobile robot navigation","author":"koren","year":"1991","journal-title":"Proceedings of the IEEE International Conference on Robotics and Automation"},{"key":"ref26","article-title":"Dynamic range improvement through multiple exposures","author":"robertson","year":"1999","journal-title":"Proceedings of the IEEE International Conference on Image Processing"},{"key":"ref25","article-title":"Kilobot: A low cost scalable robot system for collective behaviors","author":"rubenstein","year":"2012","journal-title":"Proceedings of the IEEE International Conference on Robotics and Automation"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2018,5,21]]},"location":"Brisbane, QLD","end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08463215.pdf?arnumber=8463215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T18:07:15Z","timestamp":1751998035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8463215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8463215","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}