{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:29:35Z","timestamp":1730266175747,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533775","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Emergence of Different Modes of Tool Use in a Reaching and Dragging Task"],"prefix":"10.1109","author":[{"given":"Khuong","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Yoonsuck","family":"Choe","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.001"},{"key":"ref11","article-title":"Relational tool use learning by a robot in a real and simulated world","author":"wicaksono","year":"2016","journal-title":"Proceedings of ACRA"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640811"},{"key":"ref13","article-title":"Emergent tool use from multi -agent autocurricula","author":"baker","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280564"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727766"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727765"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965913"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851821"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-33458-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1159\/000295151"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/srep33089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.anbehav.2014.11.022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329826"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2011.2177660"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10071-007-0108-1"},{"key":"ref9","volume":"1","author":"gibson","year":"1977","journal-title":"The Theory of Affordances"},{"journal-title":"Perception and action From sensorimotor learning to intelligent tool-use behavior","year":"2019","author":"nguyen","key":"ref1"},{"key":"ref20","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref21","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref23","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"journal-title":"Pytorch implementations of reinforcement learning algorithms","year":"2018","author":"kostrikov","key":"ref25"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533775.pdf?arnumber=9533775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:08Z","timestamp":1652197568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533775","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}