{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:44:24Z","timestamp":1771958664194,"version":"3.50.1"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"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":[[2018,12]]},"DOI":"10.1109\/robio.2018.8665177","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T20:01:56Z","timestamp":1552939316000},"page":"648-653","source":"Crossref","is-referenced-by-count":11,"title":["Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration"],"prefix":"10.1109","author":[{"given":"Tingguang","family":"Li","sequence":"first","affiliation":[{"name":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Pan","sequence":"additional","affiliation":[{"name":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Delong","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max Q.-H.","family":"Meng","sequence":"additional","affiliation":[{"name":"The Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref10","first-page":"441","article-title":"Bias in natural actor-critic algorithms","author":"thomas","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref6","first-page":"3675","article-title":"Hier-archical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463213"},{"key":"ref5","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"AAAI"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"6","article-title":"A deep hierarchical approach to lifelong learning in minecraft","volume":"3","author":"tessler","year":"2017","journal-title":"AAAI"},{"key":"ref2","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","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"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"}],"event":{"name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2018,12,12]]},"end":{"date-parts":[[2018,12,15]]}},"container-title":["2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8653250\/8664715\/08665177.pdf?arnumber=8665177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T20:59:45Z","timestamp":1769115585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8665177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/robio.2018.8665177","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}