{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:03:50Z","timestamp":1762841030167,"version":"build-2065373602"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Department of The Air Force","award":["FA8750-23-C-0509"],"award-info":[{"award-number":["FA8750-23-C-0509"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lcsys.2025.3629008","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T18:38:13Z","timestamp":1762281493000},"page":"2501-2506","source":"Crossref","is-referenced-by-count":0,"title":["Feedback for Improved Hierarchical Reinforcement Learning With Timed Subgoals"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8773-926X","authenticated-orcid":false,"given":"Yajie","family":"Bao","sequence":"first","affiliation":[{"name":"Department of Research and Development, Intelligent Fusion Technology, Inc., Germantown, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1834-5456","authenticated-orcid":false,"given":"Dan","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Research and Development, Intelligent Fusion Technology, Inc., Germantown, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2656-9380","authenticated-orcid":false,"given":"Genshe","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Research and Development, Intelligent Fusion Technology, Inc., Germantown, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4130-7925","authenticated-orcid":false,"given":"Hao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV, USA"}]},{"given":"Samson","family":"Badlia","sequence":"additional","affiliation":[{"name":"Advanced Planning and Autonomous C2 System Branch, Air Force Research Laboratory, Rome, NY, USA"}]},{"given":"Simon","family":"Khan","sequence":"additional","affiliation":[{"name":"Advanced Planning and Autonomous C2 System Branch, Air Force Research Laboratory, Rome, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6894-6108","authenticated-orcid":false,"given":"Erik","family":"Blasch","sequence":"additional","affiliation":[{"name":"Air Force Office of Scientific Research, Air Force Research Laboratory, Arlington, VA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4768-9365","authenticated-orcid":false,"given":"Khanh","family":"Pham","sequence":"additional","affiliation":[{"name":"Space Vehicle Directorate, Air Force Research Laboratory, Kirtland Air Force Base, New Mexico, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9655004"},{"key":"ref2","first-page":"1","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kulkarni"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812179"},{"key":"ref4","article-title":"Stop regressing: Training value functions via classification for scalable deep RL","author":"Farebrother","year":"2024","journal-title":"arXiv:2403.03950"},{"key":"ref5","article-title":"Learning multi-level hierarchies with hindsight","author":"Levy","year":"2017","journal-title":"arXiv:1712.00948"},{"key":"ref6","article-title":"Bidirectional-reachable hierarchical reinforcement learning with mutually responsive policies","author":"Luo","year":"2024","journal-title":"arXiv:2406.18053"},{"key":"ref7","first-page":"21732","article-title":"Hierarchical reinforcement learning with timed subgoals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"G\u00fcrtler"},{"key":"ref8","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref9","first-page":"1","article-title":"Hierarchical reinforcement learning with targeted causal interventions","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Khorasani"},{"key":"ref10","first-page":"1","article-title":"Hierarchical reinforcement learning with uncertainty-guided diffusional subgoals","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128715"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26213"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3539097"},{"key":"ref14","first-page":"51755","article-title":"Probabilistic subgoal representations for hierarchical reinforcement learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref15","article-title":"Inter-level cooperation in hierarchical reinforcement learning","author":"Kreidieh","year":"2019","journal-title":"arXiv:1912.02368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3425809"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3574162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2025.3529902"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782633\/10939047\/11224905.pdf?arnumber=11224905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T06:01:03Z","timestamp":1762840863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11224905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2025.3629008","relation":{},"ISSN":["2475-1456"],"issn-type":[{"type":"electronic","value":"2475-1456"}],"subject":[],"published":{"date-parts":[[2025]]}}}