{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:26:42Z","timestamp":1730266002994,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892189","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:56:04Z","timestamp":1664553364000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["HRL2E: Hierarchical Reinforcement Learning with Low-level Ensemble"],"prefix":"10.1109","author":[{"given":"You","family":"Qin","sequence":"first","affiliation":[{"name":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University,Department of Control and Systems Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1162\/neco.1994.6.2.181"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref10","article-title":"Learning multi-level hierarchies with hindsight","author":"levy","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Landmark-guided subgoal generation in hierarchical reinforcement learning","volume":"34","author":"kim","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Generating adjacency-constrained subgoals in hierarchical reinforcement learning","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","author":"li","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Hierarchical reinforcement learning for zero-shot generalization with subtask dependencies","author":"sohn","year":"2018","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref17","article-title":"Learnings options end-to-end for continuous action tasks","author":"klissarov","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Option discovery using deep skill chaining","author":"bagaria","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref19","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"gupta","year":"2019","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICNN.1994.374138"},{"key":"ref4","first-page":"3131","article-title":"I2hrl: Interactive infiuence-based hierarchical reinforcement learning","author":"wang","year":"2020","journal-title":"Proceedings of the 29th International Joint Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1609\/aaai.v33i01.33015933"},{"key":"ref3","article-title":"Why does hierarchy (sometimes) work so well in reinforcement learning?","author":"nachum","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref29"},{"key":"ref5","first-page":"176","article-title":"Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning","author":"anschel","year":"2017","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref7","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref9","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref20","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref22","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","volume":"29","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Ucb exploration via q-ensembles","author":"chen","year":"2017","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/TNNLS.2021.3087733"},{"key":"ref23","first-page":"6131","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","author":"lee","year":"2021","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1023\/A:1013689704352"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1016\/j.tcs.2009.01.016"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892189.pdf?arnumber=9892189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T18:39:52Z","timestamp":1670265592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892189","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}