{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:26:38Z","timestamp":1784823998533,"version":"3.55.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["92248303"],"award-info":[{"award-number":["92248303"]}],"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":["62373242"],"award-info":[{"award-number":["62373242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/lra.2024.3490392","type":"journal-article","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T17:26:15Z","timestamp":1730481975000},"page":"11690-11697","source":"Crossref","is-referenced-by-count":4,"title":["Constrained Dirichlet Distribution Policy: Guarantee Zero Constraint Violation Reinforcement Learning for Continuous Robotic Control"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5769-2093","authenticated-orcid":false,"given":"Jianming","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2961-2997","authenticated-orcid":false,"given":"Zhanxiang","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8901-9335","authenticated-orcid":false,"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence and AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref7","article-title":"Lyapunov-based safe policy optimization for continuous control","author":"Chow","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3155374"},{"key":"ref9","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8460547"},{"key":"ref11","first-page":"397","article-title":"Escaping from zero gradient: Revisiting action-constrained reinforcement learning via Frank-Wolfe policy optimization","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Lin","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5599"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3284378"},{"key":"ref14","article-title":"DFWLayer: Differentiable Frank-Wolfe optimization layer","volume-title":"Proc. 2nd Tiny Papers Track ICLR 2024","author":"Liu","year":"2024"},{"key":"ref15","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"issue":"167","key":"ref16","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref18","first-page":"20423","article-title":"SAUT RL: Almost surely safe reinforcement learning using state augmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sootla","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref20","article-title":"ShieldNN: A provably safe NN filter for unsafe NN controllers","author":"Ferlez","year":"2020"},{"key":"ref21","first-page":"784","article-title":"Model-free safe control for zero-violation reinforcement learning","volume-title":"Porc. 5th Annu. Conf. Robot Learn.","author":"Zhao","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063989"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3138924"},{"key":"ref24","first-page":"39842","article-title":"Generative modelling of stochastic actions with arbitrary constraints in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3166110"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3726714"},{"key":"ref27","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","year":"2018"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref31","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-004"},{"key":"ref33","first-page":"91","article-title":"Double description method revisited","volume-title":"Proc. Franco-Japanese Franco- Chin. Conf. Combinatorics Comput. Sci.","author":"Fukuda","year":"1995"},{"key":"ref34","article-title":"pycddlib python wrapper for Komei Fukuda\u2019s cddlib","author":"Troffaes","year":"2018"},{"key":"ref35","article-title":"Pybullet, A Python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"20162021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref37","article-title":"Pybullet gymperium","author":"Ellenberger","year":"20182019"},{"key":"ref38","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref39","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"issue":"268","key":"ref40","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"ref41","first-page":"159","article-title":"The Gurobi optimizer","volume":"41","author":"Bixby","year":"2007","journal-title":"Transp. Res. Part B"},{"key":"ref42","article-title":"Isaac Gym: High performance GPU-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref43","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Proc. Conf. Robot Learn.","author":"Margolis","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10726578\/10740920.pdf?arnumber=10740920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:37:09Z","timestamp":1734982629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":44,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3490392","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}