{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:17:11Z","timestamp":1784737031527,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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","award":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376122"],"award-info":[{"award-number":["62376122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4232056"],"award-info":[{"award-number":["4232056"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2021132"],"award-info":[{"award-number":["2021132"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3446371","type":"journal-article","created":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T13:23:59Z","timestamp":1724765039000},"page":"11285-11297","source":"Crossref","is-referenced-by-count":4,"title":["Discretizing Continuous Action Space With Unimodal Probability Distributions for On-Policy Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-1804","authenticated-orcid":false,"given":"Yuanyang","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Laboratory of Data Intelligence and Interdisciplinary Innovation, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-3965","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3300888"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref5","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref6","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref7","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"issue":"1","key":"ref8","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Riedmiller"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3305983"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3272068"},{"key":"ref13","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103132"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref16","first-page":"4537","article-title":"Continuous control with action quantization from demonstrations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dadashi"},{"key":"ref17","first-page":"27209","article-title":"Is bang-bang control all you need? Solving continuous control with Bernoulli policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Seyde"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3243091"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94042-7_8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6059"},{"key":"ref21","first-page":"1","article-title":"V-MPO: On-policy maximum a posteriori policy optimization for discrete and continuous control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref22","first-page":"1","article-title":"Variance reduction for policy gradient with action-dependent factorized baselines","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref23","first-page":"1","article-title":"Learning large neighborhood search policy for integer programming","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wu"},{"issue":"7","key":"ref24","first-page":"1","article-title":"Gaussian processes for ordinal regression","volume":"6","author":"Chu","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.532"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00044"},{"key":"ref27","first-page":"411","article-title":"Unimodal probability distributions for deep ordinal classification","volume-title":"Proc. Int. Conference Machine Learning","author":"Beckham"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4633963"},{"key":"ref29","article-title":"Dm_control: Software and tasks for continuous control","author":"Tassa","year":"2020","journal-title":"arXiv:2006.12983"},{"key":"ref30","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref31","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"issue":"9","key":"ref33","first-page":"1","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"Greensmith","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schulman"},{"key":"ref35","first-page":"1057","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kakade"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref37","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","volume-title":"Proc. 30th Ann. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref38","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"37","author":"Rezende"},{"key":"ref39","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":"ref40","article-title":"Implicit policy for reinforcement learning","author":"Tang","year":"2018","journal-title":"arXiv:1806.06798"},{"key":"ref41","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Chou"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21236\/AD0002209"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/78516"},{"key":"ref44","first-page":"1063","article-title":"Reinforcement learning with factored states and actions","volume":"5","author":"Sallans","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref45","first-page":"1185","article-title":"Generalized value functions for large action sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pazis"},{"key":"ref46","first-page":"3075","article-title":"Online symbolic gradient-based optimization for factored action MDPs","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Cui"},{"key":"ref47","first-page":"1380","article-title":"Implicitly regularized RL with implicit Q-values","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Vieillard"},{"key":"ref48","first-page":"1","article-title":"Learning to represent action values as a hypergraph on the action vertices","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tavakoli"},{"key":"ref49","first-page":"39842","article-title":"Generative modelling of stochastic actions with arbitrary constraints in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref50","article-title":"Discrete sequential prediction of continuous actions for deep RL","author":"Metz","year":"2017","journal-title":"arXiv:1705.05035"},{"key":"ref51","first-page":"1","article-title":"Solving continuous control via Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Seyde"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref53","first-page":"8408","article-title":"Inferring DQN structure for high-dimensional continuous control","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Sakryukin"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.10.003"},{"key":"ref55","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref56","volume-title":"OpenAI Baselines","author":"Dhariwal","year":"2017"},{"key":"ref57","first-page":"1","article-title":"Learning continuous control policies by stochastic value gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Heess"},{"key":"ref58","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref59","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ahmed"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10649808.pdf?arnumber=10649808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:37Z","timestamp":1764959977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":60,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3446371","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}