{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:49:33Z","timestamp":1770468573426,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tii.2024.3391934","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T17:47:13Z","timestamp":1715795233000},"page":"10706-10716","source":"Crossref","is-referenced-by-count":4,"title":["Safe Multiagent Learning With Soft Constrained Policy Optimization in Real Robot Control"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2722-3779","authenticated-orcid":false,"given":"Shangding","family":"Gu","sequence":"first","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7719-6505","authenticated-orcid":false,"given":"Dianye","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7868-1262","authenticated-orcid":false,"given":"Muning","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-592X","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"School of Computation, Information and Technology, Technical University of Munich, Garching, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3159570"},{"key":"ref2","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022"},{"key":"ref3","article-title":"Updet: Universal multi-agent RL via policy decoupling with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2020"},{"key":"ref4","first-page":"9041","article-title":"Policy diagnosis via measuring role diversity in cooperative multi-agent RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1280341"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref7","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103905"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_10"},{"key":"ref11","first-page":"483","article-title":"Safe multi-agent reinforcement learning via shielding","volume-title":"Proc. 20th Int. Conf. Auton. Agents MultiAgent Syst.","author":"ElSayed-Aly","year":"2021"},{"key":"ref12","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Achiam","year":"2017"},{"key":"ref13","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11040081"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3152724"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref19","article-title":"Safe multi-agent reinforcement learning for formation control without individual reference targets","author":"Dawood","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref21","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"key":"ref22","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1592434.1592436"},{"key":"ref24","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","first-page":"715","article-title":"Learning multi-agent state space representations","volume-title":"Proc. 9th Int. Conf. Auton. Agents Multiagent Syst.","volume":"1","author":"Hauwere","year":"2010"},{"key":"ref26","first-page":"158","article-title":"Assured deep multi-agent reinforcement learning for safe robotic systems","volume-title":"Proc. Int. Conf. Agents Artif. Intell.","author":"Riley","year":"2021"},{"key":"ref27","article-title":"Verification of probabilistic real-time systems","volume-title":"Proc. Real-Time Syst. Summer Sch.","author":"Parker","year":"2013"},{"key":"ref28","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref29","first-page":"2004","article-title":"Subgradient methods","volume":"2004","author":"Boyd","year":"2003"},{"key":"ref30","article-title":"Constrained differential optimization","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Platt","year":"1987"},{"key":"ref31","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke","year":"2020"},{"key":"ref32","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref34","first-page":"24611","article-title":"The surprising effectiveness of mappo in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref35","article-title":"Is independent learning all you need in the starcraft multi-agent challenge","author":"de Witt","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2723903"},{"issue":"3.2","key":"ref37","article-title":"Ros: An open-source robot operating system","volume-title":"Proc. ICRA Workshop Open Source Softw.","volume":"3","author":"Quigley","year":"2009"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10666802\/10530650.pdf?arnumber=10530650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:54:01Z","timestamp":1735588441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":37,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tii.2024.3391934","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}