{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:45:30Z","timestamp":1729637130598,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053393","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"3932-3936","source":"Crossref","is-referenced-by-count":3,"title":["Learning Diverse Sub-Policies via a Task-Agnostic Regularization on Action Distributions"],"prefix":"10.1109","author":[{"given":"Liangyu","family":"Huo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zulin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2295","article-title":"A laplacian framework for option discovery in reinforcement learning","author":"machado","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"article-title":"Stochastic neural networks for hierarchical reinforcement learning","year":"2017","author":"florensa","key":"ref11"},{"key":"ref12","first-page":"3307","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"Latent space policies for hierarchical reinforcement learning","year":"2018","author":"haarnoja","key":"ref13"},{"key":"ref14","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"},{"article-title":"Meta learning shared hierarchies","year":"2017","author":"frans","key":"ref15"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10744","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"tessler","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref5","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"3486","article-title":"Strategic attentive writer for learning macro-actions","author":"vezhnevets","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning and transfer of modulated locomotor controllers, 2016","year":"0","author":"heess","key":"ref7"},{"key":"ref2","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1998","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891792"},{"key":"ref9","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume":"70","author":"vezhnevets","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"article-title":"The arcade learning environment: An evaluation platform for general agents","year":"2012","author":"bellemare","key":"ref20"},{"key":"ref22","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053393.pdf?arnumber=9053393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:27:37Z","timestamp":1696015657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053393\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053393","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}