{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:02:33Z","timestamp":1762351353975,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"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":[[2022,12,5]]},"DOI":"10.1109\/robio55434.2022.10011930","type":"proceedings-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T13:51:38Z","timestamp":1674049898000},"page":"1335-1340","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy"],"prefix":"10.1109","author":[{"given":"Xin","family":"Xu","sequence":"first","affiliation":[{"name":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124"}]},{"given":"Guoyu","family":"Zuo","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124"}]},{"given":"Jiangeng","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124"}]},{"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Faculty of Information,Beijing,China,100124"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Learning multi-level hierarchies with hindsight","author":"levy","year":"2019","journal-title":"ICLRE"},{"key":"ref12","article-title":"Learning multi-level hierarchies with hindsight","author":"levy","year":"2019","journal-title":"ICLRE"},{"key":"ref13","article-title":"Semi-parametric topological memory for navigation","author":"savinov","year":"2018","journal-title":"ICLRE"},{"key":"ref14","first-page":"1942","article-title":"Mapping state space using landmarks for universal goal reaching","volume":"32","author":"zhiao","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"7750","article-title":"Maximum entropy gain exploration for long horizon multi-goal reinforcement learning","author":"pitis","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"Learning subgoal representations with slow dynamics","author":"siyuan","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref18","first-page":"28336","article-title":"Landmark-guided subgoal generation in hierarchical reinforcement learning","volume":"34","author":"kim","year":"2021","journal-title":"Advances in neural information processing systems"},{"journal-title":"Efficient Hierarchical Exploration with Stable Subgoal Representation Learning","year":"2021","author":"li","key":"ref19"},{"key":"ref4","article-title":"Learning to adapt in dynamic, real-world environments through meta reinforcement learning","author":"anusha","year":"2019","journal-title":"ICLRE"},{"key":"ref3","article-title":"Qt-opt.Scalable deep reinforcement learning for vision-based robotic manipulation","author":"dmitry","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Learning to adapt in dynamic, real-world environments through meta reinforcement learning","author":"anusha","year":"2019","journal-title":"ICLRE"},{"key":"ref5","first-page":"12611","article-title":"Learning latent landmarks for planning","author":"lunjun","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Generating adjacency constrained subgoals in hierarchical reinforcement learning","author":"tianren","year":"0","journal-title":"Advances in Neural Information"},{"key":"ref7","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1126\/science.aar6404","article-title":"A general reinforcement learning algorithm that masters chess, shogi, and go through self-play","volume":"362","author":"david","year":"2018","journal-title":"Science"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","volume":"588","author":"julian","year":"2020","journal-title":"Nature"},{"key":"ref9","article-title":"Exploration by randomnetwork distillation","author":"yuri","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref21","first-page":"1009","article-title":"Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory em-beddings","author":"co-reyes","year":"0","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2022,12,5]]},"location":"Jinghong, China","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10011626\/10011636\/10011930.pdf?arnumber=10011930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T16:51:12Z","timestamp":1676911872000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/robio55434.2022.10011930","relation":{},"subject":[],"published":{"date-parts":[[2022,12,5]]}}}