{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:34:46Z","timestamp":1787013286985,"version":"build-2736575974"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Mobile Robotics: Enabling a Pervasive Technology of the Future","award":["EP\/M019918\/1"],"award-info":[{"award-number":["EP\/M019918\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tnnls.2020.2977924","type":"journal-article","created":{"date-parts":[[2020,3,23]],"date-time":"2020-03-23T22:16:27Z","timestamp":1585001787000},"page":"166-176","source":"Crossref","is-referenced-by-count":42,"title":["Learning With Stochastic Guidance for Robot Navigation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8593-2277","authenticated-orcid":false,"given":"Linhai","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yishu","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1537-8834","authenticated-orcid":false,"given":"Sen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phil","family":"Blunsom","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0413-5327","authenticated-orcid":false,"given":"Zhihua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8341-6399","authenticated-orcid":false,"given":"Changhao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Markham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6236-9645","authenticated-orcid":false,"given":"Niki","family":"Trigoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.07.004"},{"key":"ref38","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2653942"},{"key":"ref32","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref30","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"2188","article-title":"Variational inference for Monte Carlo objectives","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"2638","article-title":"Local expectation gradients for black box variational inference","author":"aueb","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Q-prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref34","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref40","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"arXiv 1703 07326"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3233\/ICG-1995-18207"},{"key":"ref12","first-page":"639","article-title":"A constructive definition of Dirichlet priors","volume":"4","author":"sethuraman","year":"1994","journal-title":"Stat Sin"},{"key":"ref13","first-page":"610","article-title":"A stick-breaking likelihood for categorical data analysis with latent Gaussian models","volume":"22","author":"khan","year":"2012","journal-title":"Proc 15th Int Conf Artif Intell Statist"},{"key":"ref14","first-page":"2410","article-title":"Discovering discrete latent topics with neural variational inference","author":"miao","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","article-title":"Neural variational inference and learning in belief networks","author":"mnih","year":"2014","journal-title":"arXiv 1402 0030"},{"key":"ref16","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref17","article-title":"Planning and control in unstructured terrain","author":"gerkey","year":"2008","journal-title":"Proc of the ICRA Workshop on Path Planning and Costmaps"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/2200000070"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202141"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2014.6932662"},{"key":"ref7","first-page":"1080","article-title":"Probabilistic robot navigation in partially observable environments","volume":"95","author":"simmons","year":"1995","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref9","volume":"2","author":"\u00e5str\u00f6m","year":"1995","journal-title":"PID Controllers Theory Design and Tuning"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461203"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref24","article-title":"Towards monocular vision based obstacle avoidance through deep reinforcement learning","author":"xie","year":"2017","journal-title":"arXiv 1706 09829 [cs]"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2003.808179"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2731371"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9312808\/09044614.pdf?arnumber=9044614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:53:01Z","timestamp":1652179981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9044614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":40,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2977924","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}