{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:01:30Z","timestamp":1782835290513,"version":"3.54.5"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,24]],"date-time":"2023-09-24T00:00:00Z","timestamp":1695513600000},"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":[[2023,9,24]]},"DOI":"10.1109\/itsc57777.2023.10422469","type":"proceedings-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T23:32:39Z","timestamp":1707867159000},"page":"4114-4120","source":"Crossref","is-referenced-by-count":10,"title":["Robust Driving Policy Learning with Guided Meta Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kanghoon","family":"Lee","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Systems Intelligence Laboratory (SILAB),South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiachen","family":"Li","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford Intelligent Systems Laboratory (SISL),CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Isele","sequence":"additional","affiliation":[{"name":"Honda Research Institute USA,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinkyoo","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,Systems Intelligence Laboratory (SILAB),South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kikuo","family":"Fujimura","sequence":"additional","affiliation":[{"name":"Honda Research Institute USA,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykel J.","family":"Kochendorfer","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford Intelligent Systems Laboratory (SISL),CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2016.xii.029"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811635"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995818"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957722"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564518"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139219"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/1025349"},{"key":"ref13","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","author":"Conti","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","article-title":"Diversity-driven exploration strategy for deep reinforcement learning","volume":"31","author":"Hong","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Attraction-repulsion actor-critic for continuous control rein-forcement learning","author":"Doan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Effective diversity in population based reinforcement learning","author":"Parker-Holder","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","article-title":"Multi-critic actor learning: Teaching RL policies to act with style","volume-title":"International Conference on Learning Representations","author":"Mysore","year":"2022"},{"key":"ref18","article-title":"Discovering diverse multi-agent strategic behavior via reward randomization","author":"Tang","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref19","article-title":"Collaborating with humans without human data","author":"Strouse","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3091477"},{"key":"ref21","article-title":"Trajectory diversity for zero-shot coordination","volume-title":"International Conference on Machine Learning (ICML)","author":"Lupu"},{"key":"ref22","first-page":"434","article-title":"Open-ended learning in symmetric zero-sum games","volume-title":"International Conference on Machine Learning","author":"Balduzzi"},{"key":"ref23","article-title":"Semantically adversarial driving scenario generation with explicit knowledge integration","author":"Ding","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC57359.2022.00018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294396"},{"key":"ref26","article-title":"Dynamic program-ming for partially observable stochastic games","volume-title":"AAAI Conference on Artificial Intelligence (AAAI)","author":"Hansen"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref29","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Mnih"}],"event":{"name":"2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)","location":"Bilbao, Spain","start":{"date-parts":[[2023,9,24]]},"end":{"date-parts":[[2023,9,28]]}},"container-title":["2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10420842\/10420843\/10422469.pdf?arnumber=10422469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:50:01Z","timestamp":1709466601000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,24]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/itsc57777.2023.10422469","relation":{},"subject":[],"published":{"date-parts":[[2023,9,24]]}}}