{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:48:48Z","timestamp":1729626528069,"version":"3.28.0"},"reference-count":23,"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\/iros45743.2020.9341629","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"5497-5503","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning in Latent Action Sequence Space"],"prefix":"10.1109","author":[{"given":"Heecheol","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masanori","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kosuke","family":"Miyoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoharu","family":"Iwata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Yamakawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"article-title":"Favae: Sequence disentanglement using information bottleneck principle","year":"2019","author":"yamada","key":"ref11"},{"key":"ref12","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref13","first-page":"3486","article-title":"Strategic attentive writer for learning macro-actions","author":"vezhnevets","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref14","first-page":"2133","article-title":"Dynamic action repetition for deep reinforcement learning","author":"lakshminarayanan","year":"2017","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI)"},{"article-title":"Deep reinforcement learning with macro-actions","year":"2016","author":"durugkar","key":"ref15"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"journal-title":"Temporal Abstraction in Reinforcement Learning","year":"2000","author":"precup","key":"ref18"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10916","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref4","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning to walk via deep reinforcement learning","year":"2018","author":"haarnoja","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref8","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"},{"key":"ref7","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref9","article-title":"Learning to repeat: Fine grained action repetition for deep reinforcement learning","author":"sharma","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"article-title":"Time series segmentation through automatic feature learning","year":"2018","author":"lee","key":"ref20"},{"key":"ref22","article-title":"Learning hierarchical features from generative models","author":"zhao","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Understanding disentangling in -vae","author":"burgess","year":"2018","journal-title":"Neural Information Processing Systems (NIPS) 2017 Disentangled Workshop"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref23"}],"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\/09341629.pdf?arnumber=9341629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T04:16:16Z","timestamp":1671250576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341629","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}