{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:35:12Z","timestamp":1730205312697,"version":"3.28.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/cec60901.2024.10611988","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:55:15Z","timestamp":1723139715000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Extended Generative Adversarial Imitation Learning for Autonomous Agents in Minecraft Game"],"prefix":"10.1109","author":[{"given":"Hyung-Jun","family":"Moon","sequence":"first","affiliation":[{"name":"Yonsei University,Department of Artificial Inteligence,Seoul,Korea,03722"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Bae","family":"Cho","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Computer Science,Seoul,Korea,03722"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3144867"},{"issue":"99","key":"ref2","first-page":"1","article-title":"Imitation learning: Progress, taxonomies and challenges","author":"Zheng","year":"2022","journal-title":"IEEE Trans. on Neural Networks and Learning Systems"},{"key":"ref3","first-page":"259","article-title":"Retrospective on the 2021 minerl BASALT competition on learning from human feedback","author":"Shah","year":"2022","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref4","first-page":"203","article-title":"Retrospective analysis of the 2019 MineRL competition on sample efficient reinforcement learning","author":"Milani","year":"2020","journal-title":"NeurIPS 2019 Competition and Demonstration Track"},{"key":"ref5","first-page":"13","article-title":"Minerl diamond 2021 competition: Overview, results, and lessons learned","author":"Kanervisto","year":"2022","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/339"},{"key":"ref7","article-title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","author":"Novoseller","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","author":"Yuan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490398"},{"key":"ref11","first-page":"2656","article-title":"Reinforcement learning for constrained markov decision processes","volume-title":"Int. Conf. on Artificial Intelligence and Statistics","author":"Gattami","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3036471"},{"key":"ref13","article-title":"Automatic financial trading agent for low-risk portfolio management using deep reinforcement learning","volume-title":"arXiv preprint","author":"Shin","year":"2019"},{"key":"ref14","first-page":"4572","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"NeurIPS"},{"key":"ref15","first-page":"12805","article-title":"f-gail: Learning f-divergence for generative adversarial imitation learning","volume":"33","author":"Zhang","year":"2020","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Adail: Adaptive adversarial imitation learning","author":"Lu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"3813","article-title":"Infogail: Interpretable imitation learning from visual demonstrations","volume":"30","author":"Li","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Directed-info gail: Learning hierarchical policies from unsegmented demonstrations using directed information","author":"Sharma","year":"2018","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow","author":"Peng","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.04.092"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01242"},{"key":"ref22","article-title":"Sqil: Imitation learning via reinforcement learning with sparse rewards","author":"Reddy","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636363"},{"key":"ref24","first-page":"10925","article-title":"Intrinsic reward driven imitation learning via generative model","volume-title":"Int. Conf. on Machine Learning","author":"Yu","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.08.058"},{"key":"ref26","article-title":"Disagreement-regularized imitation learning","volume-title":"Int. Conf. on Learning Representations","author":"Brantley","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03493-1_49"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/452"},{"key":"ref29","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231600"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CEC45853.2021.9505001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061374"},{"key":"ref33","first-page":"2458","article-title":"Inverse reinforcement learning from a gradient-based learner","volume":"33","author":"Ramponi","year":"2020","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26766"},{"key":"ref35","article-title":"Goal-conditioned imitation learning","volume":"32","author":"Ding","year":"2019","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.053"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103091"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/405"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3227738"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE Congress on Evolutionary Computation (CEC)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609966\/10611750\/10611988.pdf?arnumber=10611988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:23:46Z","timestamp":1723350226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/cec60901.2024.10611988","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}