{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:19:59Z","timestamp":1766578799618,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160698","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T13:20:56Z","timestamp":1688476856000},"page":"9421-9427","source":"Crossref","is-referenced-by-count":10,"title":["Conflict-constrained Multi-agent Reinforcement Learning Method for Parking Trajectory Planning"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,P.R. China,100081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiling","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,P.R. China,100081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,P.R. China,100081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Song","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology,Beijing,P.R. China,100081"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909359210"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47358-7_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2990294"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICM46511.2021.9385634"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17466"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2687047"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995971"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3161699"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340876"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Int Conference on Machine Learning"},{"key":"ref23","first-page":"25636","article-title":"Reachability constrained reinforce-ment learning","author":"yu","year":"2022","journal-title":"Int Conference on Machine Learning"},{"key":"ref26","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Reward constrained policy optimization","author":"tessler","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref22","first-page":"22","article-title":"Constrained policy op-timization","author":"achiam","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref21","article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","author":"ma","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"An Environment for Autonomous Driving Decision-Making","year":"2018","author":"leurent","key":"ref27"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12239-020-0085-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1883\/1\/012111"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","article-title":"Optimization-based trajectory planning for autonomous parking with irregularly placed obstacles: A lightweight iterative framework","author":"li","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197132"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160698.pdf?arnumber=10160698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T13:33:29Z","timestamp":1690205609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160698","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}