{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:07:16Z","timestamp":1760609236409,"version":"3.44.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968252","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1003-1009","source":"Crossref","is-referenced-by-count":2,"title":["Graph-Based Design of Hierarchical Reinforcement Learning Agents"],"prefix":"10.1109","author":[{"given":"Davide","family":"Tateo","sequence":"first","affiliation":[{"name":"Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u0130dil Su","family":"Erdenli\u011f","sequence":"additional","affiliation":[{"name":"Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Bonarini","sequence":"additional","affiliation":[{"name":"Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc NIPS2"},{"key":"ref11","article-title":"Hierarchical actor-critic","author":"levy","year":"2017","journal-title":"arXiv preprint arXiv 1712 00948"},{"key":"ref12","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"arXiv preprint arXiv 1704 03012"},{"key":"ref13","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"},{"journal-title":"Mushroom Hierarchical","year":"0","author":"tateo","key":"ref14"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"bartlett","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref18","first-page":"1607","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Proc AAAI2010"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref3","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"1997","journal-title":"Proc NIPS"},{"key":"ref6","first-page":"226","article-title":"Hierarchical policy gradient algorithms","author":"ghavamzadeh","year":"2003","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref8","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Proc NIPS"},{"key":"ref7","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"arXiv preprint arXiv 1703 01281"},{"key":"ref2","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref1","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc ICML2015"},{"key":"ref9","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc AAAI2017"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968252.pdf?arnumber=8968252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:35:12Z","timestamp":1755714912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968252","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}