{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:58:14Z","timestamp":1782406694324,"version":"3.54.5"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611037","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"2859-2865","source":"Crossref","is-referenced-by-count":5,"title":["Learning Adaptive Safety for Multi-Agent Systems"],"prefix":"10.1109","author":[{"given":"Luigi","family":"Berducci","sequence":"first","affiliation":[{"name":"TU Wien,Institute of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,Dept. of Electrical and Systems Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Mangharam","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,Dept. of Electrical and Systems Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radu","family":"Grosu","sequence":"additional","affiliation":[{"name":"TU Wien,Institute of Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3232542"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3233322"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3216996"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref7","article-title":"Multi-agent reinforcement learning guided by signal temporal logic specifications","author":"Wang","year":"2023"},{"key":"ref8","article-title":"Temporal logic guided safe reinforcement learning using control barrier functions","author":"Li","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3074895"},{"key":"ref10","article-title":"Learning safe multi-agent control with decentralized neural barrier certificates","author":"Qin","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3249564"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482626"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9993001"},{"key":"ref14","article-title":"Consolidated control barrier functions: Synthesis and online verification via adaptation under input constraints","author":"Black","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304395"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref17","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref18","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"International Conference on Machine Learning","author":"Stooke"},{"issue":"1","key":"ref19","first-page":"2","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.11.154"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482848"},{"key":"ref22","first-page":"77","article-title":"F1tenth: An open-source evaluation environment for continuous control and reinforcement learning","author":"O\u2019Kelly","year":"2020","journal-title":"NeurIPS 2019 Competition and Demonstration Track"},{"key":"ref23","article-title":"Omnisafe: An infrastructure for accelerating safe reinforcement learning research","author":"Ji","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref25","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref26","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref28","first-page":"20423","article-title":"Saut\u00e9 rl: Almost surely safe reinforcement learning using state augmentation","volume-title":"International Conference on Machine Learning","author":"Sootla"},{"key":"ref29","article-title":"Robust policy optimization in deep reinforcement learning","author":"Rahman","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.021"},{"key":"ref31","volume-title":"Implementation of the pure pursuit path tracking algorithm","author":"Coulter","year":"1992"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20265"},{"issue":"1","key":"ref33","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"A lyapunov-based approach to safe reinforcement learning","volume":"31","author":"Chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref37","first-page":"36593","article-title":"Enforcing hard constraints with soft barriers: Safe reinforcement learning in unknown stochastic environments","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812398"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992744"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2659727"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3000748"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029455"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611037.pdf?arnumber=10611037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T06:03:43Z","timestamp":1723269823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611037","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}