{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:04:26Z","timestamp":1740099866057,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,9,28]],"date-time":"2020-09-28T00:00:00Z","timestamp":1601251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,28]],"date-time":"2020-09-28T00:00:00Z","timestamp":1601251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,28]],"date-time":"2020-09-28T00:00:00Z","timestamp":1601251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,28]]},"DOI":"10.1109\/rcar49640.2020.9303280","type":"proceedings-article","created":{"date-parts":[[2020,12,30]],"date-time":"2020-12-30T21:55:00Z","timestamp":1609365300000},"page":"74-80","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Reinforcement Learning Based on Continuous Subgoal Space"],"prefix":"10.1109","author":[{"given":"Chen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Fanyu","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Shuzhi Sam","family":"Ge","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31 Annual Conference on Neural Information Processing Systems 2018 NeurlPS 2018"},{"journal-title":"Learning multilevel hierarchies with hindsight","year":"2019","author":"levy","key":"ref11"},{"journal-title":"Minimalistic gridworld environment for openai gym","year":"2018","author":"chevalier-boisvert","key":"ref12"},{"key":"ref13","article-title":"Playing atari with deep reinforcement learning","volume":"abs 1312 5602","author":"mnih","year":"2013","journal-title":"CoRR"},{"journal-title":"Continuous control with deep reinforcement learning","year":"2016","author":"lillicrap","key":"ref14"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ICML 2015"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"journal-title":"High-dimensional continuous control using generalized advantage estimation","year":"2016","author":"schulman","key":"ref18"},{"key":"ref19","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref4","first-page":"2424","article-title":"Learning to navigate in cities without a map","author":"mirowski","year":"2018","journal-title":"Advances in Neural Information Processing Systems 31 Annual Conference on Neural Information Processing Systems 2018 NeurIPS 2018"},{"journal-title":"Learning to navigate in complex environments","year":"2017","author":"mirowski","key":"ref3"},{"key":"ref6","first-page":"8846","author":"mousavian","year":"2019","journal-title":"Visual representations for semantic target driven navigation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref8","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 29 Annual Conference on Neural Information Processing Systems 2016"},{"key":"ref7","first-page":"1312","article-title":"Universal value function approximators","volume":"37","author":"schaul","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1049\/trit.2018.0008"},{"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":"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"},{"journal-title":"Meta learning shared hierarchies","year":"2018","author":"frans","key":"ref20"},{"key":"ref21","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 Annual Conference on Neural Information Processing Systems 2017"}],"event":{"name":"2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2020,9,28]]},"location":"Asahikawa, Japan","end":{"date-parts":[[2020,9,29]]}},"container-title":["2020 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303031\/9303032\/09303280.pdf?arnumber=9303280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:44Z","timestamp":1656453464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,28]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/rcar49640.2020.9303280","relation":{},"subject":[],"published":{"date-parts":[[2020,9,28]]}}}