{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:40:40Z","timestamp":1755830440162,"version":"3.44.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968584","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"2686-2692","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Explore in Motion and Interaction Tasks"],"prefix":"10.1109","author":[{"given":"Miroslav","family":"Bogdanovic","sequence":"first","affiliation":[{"name":"Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ludovic","family":"Righetti","sequence":"additional","affiliation":[{"name":"Max-Planck Institute for Intelligent Systems,Movement Generation and Control group,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning and transfer of modulated locomotor controllers","volume":"abs 1610 5182","author":"heess","year":"2016","journal-title":"CoRR"},{"key":"ref11","article-title":"Learning by playing - solving sparse reward tasks from scratch","volume":"abs 1802 10567","author":"riedmiller","year":"2018","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/4-431-31381-8_23"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","first-page":"1","article-title":"Contact-Invariant Optimization for Hand Manipulation","author":"mordatch","year":"2012","journal-title":"Eurographics\/ ACM SIGGRAPH Symposium on Computer Animation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460537"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref18","article-title":"Generating sequences with recurrent neural networks","volume":"abs 1308 850","author":"graves","year":"2013","journal-title":"CoRR"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","volume":"abs 1509 2971","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref6","first-page":"112","article-title":"Intrinsically motivated learning of hierarchical collections of skills","author":"barto","year":"2004","journal-title":"IEEE Int Conf Development and Learning and Epigenetic Robotics"},{"key":"ref5","article-title":"Parameter space noise for exploration","volume":"abs 1706 1905","author":"plappert","year":"2017","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref7","article-title":"Curiosity driven exploration of learned disentangled goal spaces","author":"laversanne-finot","year":"2018","journal-title":"arXiv preprint arXiv 1807 01521"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7763\/IJMLC.2015.V5.489"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"eaau5872","DOI":"10.1126\/scirobotics.aau5872","article-title":"Learning agile and dynamic motor skills for legged robots","volume":"4","author":"hwangbo","year":"2019","journal-title":"Robotics Science"},{"key":"ref9","article-title":"Distral: Robust multitask reinforcement learning","volume":"abs 1707 4175","author":"teh","year":"2017","journal-title":"CoRR"},{"journal-title":"OpenAI Baselines","year":"2017","author":"dhariwal","key":"ref20"},{"key":"ref21","article-title":"How many random seeds? statistical power analysis in deep reinforcement learning experiments","author":"colas","year":"2018","journal-title":"arXiv preprint arXiv 1806 08295"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968584.pdf?arnumber=8968584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:48Z","timestamp":1755800628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968584","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}