{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:25:39Z","timestamp":1792599939117,"version":"4.5.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968478","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"151-158","source":"Crossref","is-referenced-by-count":61,"title":["Interaction-aware Decision Making with Adaptive Strategies under Merging Scenarios"],"prefix":"10.1109","author":[{"given":"Yeping","family":"Hu","sequence":"first","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,CA,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Nakhaei","sequence":"additional","affiliation":[{"name":"Honda Research Institute,Mountain View,CA,USA,94043"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"University of California,Department of Mechanical Engineering,Berkeley,CA,USA,94720"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kikuo","family":"Fujimura","sequence":"additional","affiliation":[{"name":"Honda Research Institute,Mountain View,CA,USA,94043"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"807","article-title":"All learning is local: Multi-agent learning in global reward games","author":"chang","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref12","article-title":"CM3: Cooperative multi-goal multi-stage multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"arXiv preprint arXiv 1809 05188"},{"key":"ref13","article-title":"On a formal model of safe and scalable self-driving cars","author":"shalev-shwartz","year":"2017","journal-title":"arXiv preprint arXiv 1708 06374"},{"key":"ref14","article-title":"Tactical decision making for lane changing with deep reinforcement learning","author":"mukadam","year":"2017","journal-title":"Neural Information Processing Systems (NIPS) Conference"},{"key":"ref15","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651211"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20253"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.029"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2013.6629638"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995949"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20255"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20258"},{"key":"ref9","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968478.pdf?arnumber=8968478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T21:54:24Z","timestamp":1756245264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968478","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}