{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T19:36:55Z","timestamp":1761766615617,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852026","type":"proceedings-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T23:44:32Z","timestamp":1569887072000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["A Human-Like Agent Based on a Hybrid of Reinforcement and Imitation Learning"],"prefix":"10.1109","author":[{"given":"Rousslan Fernand","family":"Julien Dossa","sequence":"first","affiliation":[]},{"given":"Xinyu","family":"Lian","sequence":"additional","affiliation":[]},{"given":"Hirokazu","family":"Nomoto","sequence":"additional","affiliation":[]},{"given":"Takashi","family":"Matsubara","sequence":"additional","affiliation":[]},{"given":"Kuniaki","family":"Uehara","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Torcs: “The open racing car simulator","year":"2015","author":"wymann","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref13","first-page":"-387i","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32"},{"key":"ref14","article-title":"Parameter space noise for exploration","author":"plappert","year":"2017","journal-title":"CoRR"},{"key":"ref15","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"CoRR"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref16"},{"key":"ref17","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref19","article-title":"Dropout: A simple way to prevent neural networks from over tting","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","year":"2016","author":"shalev-shwartz","key":"ref3"},{"key":"ref6","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"},{"article-title":"Deep reinforcement learning approach to autonomous navigation","year":"2017","author":"vikas","key":"ref5"},{"key":"ref8","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref7","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2012.10.001"},{"article-title":"Using keras and deep deterministic policy gradient to play torcs","year":"2016","author":"lau","key":"ref20"},{"article-title":"Gym torcs","year":"2016","author":"yoshida","key":"ref22"},{"article-title":"Torcs for reinforcement learning","year":"0","author":"you","key":"ref21"},{"article-title":"Openai baselines","year":"2017","author":"dhariwal","key":"ref23"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852026.pdf?arnumber=8852026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:54:04Z","timestamp":1658080444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852026","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}