{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:04:48Z","timestamp":1771329888179,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007917","name":"ARS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007917","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,6]]},"DOI":"10.1109\/icar53236.2021.9659344","type":"proceedings-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T20:42:02Z","timestamp":1641415322000},"page":"640-645","source":"Crossref","is-referenced-by-count":27,"title":["Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks"],"prefix":"10.1109","author":[{"given":"Luca","family":"Marzari","sequence":"first","affiliation":[]},{"given":"Ameya","family":"Pore","sequence":"additional","affiliation":[]},{"given":"Diego","family":"Dall'Alba","sequence":"additional","affiliation":[]},{"given":"Gerardo","family":"Aragon-Camarasa","sequence":"additional","affiliation":[]},{"given":"Alessandro","family":"Farinelli","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Fiorini","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref11","first-page":"1872","article-title":"Mastering basketball with deep reinforcement learning: An integrated curriculum training approach","author":"jia","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref12","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref14","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","author":"goecks","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90053-M"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref18","article-title":"Hierarchical actor-critic","volume":"12","author":"levy","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968488"},{"key":"ref4","article-title":"A dissection of overfitting and generalization in continuous reinforcement learning","author":"zhang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Learning to walk via deep reinforcement learning","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb2174"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8813861"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197262"},{"key":"ref22","author":"plappert","year":"2018","journal-title":"Multi-goal reinforcement learning Challenging robotics environments and request for research"},{"key":"ref21","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref25","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 20th International Conference on Advanced Robotics (ICAR)","location":"Ljubljana, Slovenia","start":{"date-parts":[[2021,12,6]]},"end":{"date-parts":[[2021,12,10]]}},"container-title":["2021 20th International Conference on Advanced Robotics (ICAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658571\/9659314\/09659344.pdf?arnumber=9659344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:39Z","timestamp":1652201799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9659344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icar53236.2021.9659344","relation":{},"subject":[],"published":{"date-parts":[[2021,12,6]]}}}