{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:28:40Z","timestamp":1730266120247,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206918","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Monoceros: A New Approach for Training an Agent to Play FPS Games"],"prefix":"10.1109","author":[{"given":"Ruiyang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beihong","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","author":"wu","year":"2017","journal-title":"5th International Conference on Learning Representations - ICLR 2017"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1162\/neco.1991.3.1.88"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1145\/1015330.1015430"},{"key":"ref13","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"3","author":"ziebart","year":"2008","journal-title":"Proceedings of the 23rd National Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.robot.2016.06.003"},{"key":"ref15","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","volume":"2","author":"goodfellow","year":"2014","journal-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37 ser ICML’15"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref19","first-page":"6536","article-title":"Random expert distillation: Imitation learning via expert policy support estimation","author":"wang","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019"},{"key":"ref4","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":"ref3","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref5","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"CoRR"},{"key":"ref8","first-page":"5085","article-title":"Arnold: An autonomous agent to play fps games","author":"chaplot","year":"2017","journal-title":"Proc the thirty-first AAAI conference on artificial intelligence AAAI"},{"key":"ref7","first-page":"2140","article-title":"Playing fps games with deep reinforcement learning","author":"lample","year":"2017","journal-title":"Proc the thirty-first AAAI conference on artificial intelligence AAAI"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1561\/9781680835397"},{"key":"ref1","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"CoRR"},{"key":"ref9","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning"},{"key":"ref20","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"CoRR"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206918.pdf?arnumber=9206918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:49:58Z","timestamp":1656452998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206918","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}