{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:37:13Z","timestamp":1765546633713,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/cog47356.2020.9231600","type":"proceedings-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T18:05:50Z","timestamp":1603303550000},"page":"558-565","source":"Crossref","is-referenced-by-count":16,"title":["Benchmarking End-to-End Behavioural Cloning on Video Games"],"prefix":"10.1109","author":[{"given":"Anssi","family":"Kanervisto","sequence":"first","affiliation":[]},{"given":"Joonas","family":"Pussinen","sequence":"additional","affiliation":[]},{"given":"Ville","family":"Hautamaki","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"NIPS"},{"key":"ref38","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref32","article-title":"superstition” in the network: Deep reinforcement learning plays deceptive games","author":"bontrager","year":"2019","journal-title":"AAAI Artificial Intelligence and Interactive Digital Entertainment"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/IROS.2010.5650345"},{"year":"2018","author":"firoiu","article-title":"At human speed: Deep reinforcement learning with action delay","key":"ref30"},{"year":"2014","author":"kingma","article-title":"Adam: A method for stochastic optimization","key":"ref37"},{"year":"2018","author":"espeholt","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","key":"ref36"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/CVPR.2016.90"},{"year":"2018","author":"hill","article-title":"Stable baselines","key":"ref34"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"AAAI"},{"year":"2019","author":"fujimoto","article-title":"Benchmarking batch deep reinforcement learning algorithms","key":"ref40"},{"year":"2016","author":"bojarski","article-title":"End to end learning for self-driving cars","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICRA.2018.8460487"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.24963\/ijcai.2019\/339"},{"year":"2019","author":"zhang","article-title":"Atari-head: Atari human eye-tracking and demonstration dataset","key":"ref14"},{"year":"2017","author":"kurin","article-title":"The atari grand challenge dataset","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CIG.2019.8847995"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/1067343.1067374"},{"key":"ref18","article-title":"Imitative learning of combat behaviours in first-person computer games","author":"gorman","year":"2007","journal-title":"CGames07"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/CIG.2018.8490398"},{"key":"ref28","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","author":"zahavy","year":"2018","journal-title":"NIPS"},{"year":"2019","author":"berner","article-title":"Dota 2 with large scale deep reinforcement learning","key":"ref4"},{"year":"2015","author":"dulac-arnold","article-title":"Deep reinforcement learning in large discrete action spaces","key":"ref27"},{"year":"2018","author":"jaderberg","article-title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","key":"ref3"},{"key":"ref6","first-page":"1","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref29","article-title":"Discrete and continuous action representation for practical rl in video games","author":"delalleau","year":"2019","journal-title":"Proc AAAI Workshop Reinforcement Learn Games"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1609\/aaai.v34i04.6144"},{"year":"2018","author":"juliani","article-title":"Unity: A general platform for intelligent agents","key":"ref8"},{"year":"2017","author":"vinyals","article-title":"Starcraft ii: A new challenge for reinforcement learning","key":"ref7"},{"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":"ref9","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"NIPS"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref1"},{"year":"2017","author":"chen","article-title":"The game imitation: Deep supervised convolutional networks for quick video game ai","key":"ref20"},{"year":"2020","author":"scheller","article-title":"Sample efficient reinforcement learning through learning from demonstrations in minecraft","key":"ref22"},{"key":"ref21","article-title":"Causal confusion in imitation learning","author":"de haan","year":"2019","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1613\/jair.3912"},{"year":"2017","author":"bukaty","article-title":"Using human gameplay to augment reinforcement learning models for crypt of the necrodancer","key":"ref26"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/TG.2018.2877047"}],"event":{"name":"2020 IEEE Conference on Games (CoG)","start":{"date-parts":[[2020,8,24]]},"location":"Osaka, Japan","end":{"date-parts":[[2020,8,27]]}},"container-title":["2020 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9222389\/9231525\/09231600.pdf?arnumber=9231600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T05:21:41Z","timestamp":1669267301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9231600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/cog47356.2020.9231600","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}