{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:22:27Z","timestamp":1755800547953,"version":"3.28.0"},"reference-count":34,"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\/cec60901.2024.10612178","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":1,"title":["Improving Generalization in Game Agents with Data Augmentation in Imitation Learning"],"prefix":"10.1109","author":[{"given":"Derek","family":"Yadgaroff","sequence":"first","affiliation":[{"name":"Uppsala University"}]},{"given":"Alessandro","family":"Sestini","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Konrad","family":"Tollmar","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Ayca","family":"Ozcelikkale","sequence":"additional","affiliation":[{"name":"Uppsala University"}]},{"given":"Linus","family":"Gissl\u00e9n","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3313039"},{"key":"ref2","article-title":"Online game testing using scenario-based control of massive virtual users","volume-title":"International Conference on Advanced Communication Technology","author":"Cho","year":"2010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231552"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619048"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cog57401.2023.10333234"},{"key":"ref9","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","volume-title":"NIPS Workshop on DRL","author":"Justesen","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3226910"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref12","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"Xie","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","author":"Yarats","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"907","article-title":"S4rl: Surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Conference on Robot Learning. PMLR","author":"Sinha","year":"2022"},{"key":"ref15","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Cobbe","year":"2020"},{"key":"ref16","first-page":"103","article-title":"A framework for behavioural cloning","volume":"15","author":"Bain","year":"1995","journal-title":"Machine Intelligence"},{"key":"ref17","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"2011 International Conference on Artificial Intelligence and Statistics (ICAIS)","author":"Ross","year":"2011"},{"key":"ref18","article-title":"Generative adversarial imitation learning","volume-title":"International Conference on Neural Information Processing Systems","author":"Ho","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893617"},{"key":"ref20","article-title":"Scaling imitation learning in minecraft","author":"Amiranashvili","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848091"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.2990865"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490398"},{"key":"ref24","article-title":"Inverse reinforcement learning for video games","volume-title":"NIPS Workshop on Deep Reinforcement Learning","author":"Tucker","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3555858.3555878"},{"key":"ref27","article-title":"Imitating human behaviour with diffusion models","author":"Pearce","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619084"},{"key":"ref29","article-title":"Deepcrawl: Deep reinforcement learning for turn-based strategy games","author":"Sestini","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"9052","article-title":"Teachmyagent: a benchmark for automatic curriculum learning in deep rl","volume-title":"International Conference on Machine Learning. PMLR","author":"Romac","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100258"},{"key":"ref32","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"Laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Task-relevant adversarial imitation learning","volume-title":"Conference on Robot Learning","author":"Zolna","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"}],"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\/10612178.pdf?arnumber=10612178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:26:18Z","timestamp":1723350378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10612178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/cec60901.2024.10612178","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}