{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:03:11Z","timestamp":1770915791918,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8593702","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"3110-3116","source":"Crossref","is-referenced-by-count":34,"title":["Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments"],"prefix":"10.1109","author":[{"given":"Xi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Ghadirzadeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Folkesson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marten","family":"Bjorkman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patric","family":"Jensfelt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref11","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/2897824.2925881","article-title":"Terrain-adaptive locomotion skills using deep reinforcement learning","volume":"35","author":"peng","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref13","author":"heess","year":"2017","journal-title":"Emergence of locomotion behaviours in rich environments"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref15","author":"heess","year":"2016","journal-title":"Learning and transfer of modulated locomotor controllers"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref17","author":"peng","year":"2017","journal-title":"Sim-to-real transfer of robotic control with dynamics randomization"},{"key":"ref18","author":"tobin","year":"2017","journal-title":"Domain Randomization and Generative Models for Robotic Grasping"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref4","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref3","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref6","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref5","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206046"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref2","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":"ref1","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref9","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref20","author":"bousmalis","year":"2017","journal-title":"Using simulation and domain adaptation to improve efficiency of deep robotic grasping"},{"key":"ref22","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08593702.pdf?arnumber=8593702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:51:17Z","timestamp":1598230277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8593702\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8593702","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}