{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T19:12:29Z","timestamp":1775934749117,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,5]],"date-time":"2022-06-05T00:00:00Z","timestamp":1654387200000},"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":[[2022,6,5]]},"DOI":"10.1109\/iv51971.2022.9827367","type":"proceedings-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:33:28Z","timestamp":1658259208000},"page":"1026-1032","source":"Crossref","is-referenced-by-count":5,"title":["Solving the Deadlock Problem with Deep Reinforcement Learning Using Information from Multiple Vehicles"],"prefix":"10.1109","author":[{"given":"Tsuyoshi","family":"Goto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hidenori","family":"Itaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsubasa","family":"Hirakawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takayoshi","family":"Yamashita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hironobu","family":"Fujiyoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref13","first-page":"1008","article-title":"Actor-Critic Algorithms","author":"konda","year":"2000","journal-title":"Proceeding of Neural Information Processing Systems"},{"key":"ref14","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume":"29","author":"sukhbaatar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Graph convolutional reinforcement learning","author":"jiang","year":"2018","journal-title":"arXiv preprint arXiv 1810 09076"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.65"},{"key":"ref17","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","author":"jaques","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref18","article-title":"Deep attention recurrent q-network","author":"sorokin","year":"2015","journal-title":"arXiv preprint arXiv 1512 01882"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814124"},{"key":"ref5","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534363"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569977"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","first-page":"169","article-title":"Trajectory Optimization and State Transition for Urban Automated Driving","author":"keisuke","year":"2017","journal-title":"The 3rd International Symposium on Swarm Behavior and Bio-Inspired Robotics"},{"key":"ref9","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 IEEE Intelligent Vehicles Symposium (IV)","location":"Aachen, Germany","start":{"date-parts":[[2022,6,4]]},"end":{"date-parts":[[2022,6,9]]}},"container-title":["2022 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9826996\/9826997\/09827367.pdf?arnumber=9827367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T20:05:05Z","timestamp":1659989105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9827367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iv51971.2022.9827367","relation":{},"subject":[],"published":{"date-parts":[[2022,6,5]]}}}