{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:24:38Z","timestamp":1766132678795,"version":"3.48.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246629","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"6048-6054","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications"],"prefix":"10.1109","author":[{"given":"Jiangwei","family":"Wang","sequence":"first","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyan","family":"An","sequence":"additional","affiliation":[{"name":"Vanderbilt University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songyang","family":"Han","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhili","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Mangharam","sequence":"additional","affiliation":[{"name":"University of Pennsylvania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiyi","family":"Ma","sequence":"additional","affiliation":[{"name":"Vanderbilt University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Miao","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161216"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/763"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981759"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968254"},{"article-title":"Multi-agent reinforcement learning with temporal logic specifications","year":"2021","author":"Hammond","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","year":"2016","author":"Shalev-Shwartz","key":"ref13"},{"article-title":"Reward design with language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kwon","key":"ref14"},{"article-title":"Concrete problems in ai safety","year":"2016","author":"Amodei","key":"ref15"},{"key":"ref16","first-page":"1397","article-title":"Modeling difference rewards for multiagent learning","volume-title":"AAMAS","author":"Proper"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510171"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.985"},{"key":"ref19","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","volume-title":"ICML","author":"Icarte"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-28582-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206234"},{"key":"ref23","first-page":"2228","article-title":"Learning from demonstrations using signal temporal logic","volume-title":"Conference on Robot Learning","author":"Puranic"},{"article-title":"Safe multi-agent reinforcement learning via shielding","year":"2021","author":"ElSayed-Aly","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3233\/faia200086"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30206-3_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2018.2853182"},{"article-title":"Autonomous driving using model predictive control and a kinematic bicycle vehicle model","volume-title":"Intelligent Vehicles Symposium","author":"Kong","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.02.001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483029"},{"key":"ref34","first-page":"708","article-title":"Learning for safety-critical control with control barrier functions","volume-title":"Learning for Dynamics and Control","author":"Taylor","year":"2020"},{"key":"ref35","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"NeurIPS"},{"key":"ref36","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"CoRL","author":"Dosovitskiy","year":"2017"},{"key":"ref37","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"NeurIPS"},{"article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","year":"2020","author":"Papoudakis","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/acc53348.2022.9867314"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3285442"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246629.pdf?arnumber=11246629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:20:59Z","timestamp":1766132459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246629","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}