{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:12:59Z","timestamp":1755799979219,"version":"3.44.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004012","name":"Jane and Aatos Erkko Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004012","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,26]]},"DOI":"10.1109\/cog64752.2025.11114160","type":"proceedings-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:06:42Z","timestamp":1755626802000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["On the Importance of Representation in Imitating Human-Like Gameplay"],"prefix":"10.1109","author":[{"given":"Ville","family":"Tanskanen","sequence":"first","affiliation":[{"name":"University of Helsinki,Department of Computer Science,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arto","family":"Klami","sequence":"additional","affiliation":[{"name":"University of Helsinki,Department of Computer Science,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ville","family":"Hautam\u00e4ki","sequence":"additional","affiliation":[{"name":"School of Computing, University of Eastern Finland,Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CoG57401.2023.10333200"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CoG57401.2023.10333167"},{"key":"ref4","first-page":"24639","article-title":"Video pretraining (vpt): Learning to act by watching unlabeled online videos","volume":"35","author":"Baker","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"A geometric perspective on optimal representations for reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Bellemare","year":"2019"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Interpreting emergent planning in model-free reinforcement learning","author":"Bush","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Primal wasserstein imitation learning","author":"Dadashi","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619127"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645651"},{"key":"ref11","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"International conference on machine learning","author":"Finn","year":"2016"},{"key":"ref12","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Fu","year":"2018"},{"key":"ref13","first-page":"1259","article-title":"A divergence minimization perspective on imitation learning methods","volume-title":"Conference on robot learning","author":"Kamyar","year":"2020"},{"key":"ref14","first-page":"29343","article-title":"Battle of the backbones: A large-scale comparison of pretrained models across computer vision tasks","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Goldblum","year":"2023"},{"key":"ref15","first-page":"12511","article-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline","volume-title":"International Conference on Machine Learning","author":"Hansen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231600"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893630"},{"key":"ref19","first-page":"2627","article-title":"Selecting the state-representation in reinforcement learning","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems, NIPS\u201911","author":"Maillard"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645565"},{"key":"ref21","first-page":"171","article-title":"Towards solving fuzzy tasks with human feedback: A retrospective of the minerl basalt 2022 competition","volume-title":"Proceedings of the NeurIPS 2022 Competitions Track, volume 220 of Proceedings of Machine Learning Research","author":"Milani","year":"Dec 2022"},{"key":"ref22","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv"},{"journal-title":"OpenAI","article-title":"Chatgpt: Optimizing language models for dialogue","year":"2024","key":"ref23"},{"key":"ref24","first-page":"17359","article-title":"The unsurprising effectiveness of pre-trained vision models for control","volume-title":"international conference on machine learning","author":"Parisi","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893617"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref27","first-page":"32916","article-title":"The surprising ineffectiveness of pre-trained visual representations for model-based reinforcement learning","volume":"37","author":"Schneider","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3226910"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/482"},{"key":"ref31","first-page":"3008","article-title":"Learning to summarize with human feedback","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Stiennon","year":"2020"},{"key":"ref32","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"International conference on machine learning","author":"Stooke","year":"2021"},{"key":"ref33","article-title":"Reinforcement learning: An introduction","volume-title":"A Bradford Book","author":"Sutton","year":"2018"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal transport: old and new","volume":"338","author":"Villani","year":"2009"},{"key":"ref35","first-page":"16158","article-title":"Why do pretrained language models help in downstream tasks? an analysis of head and prompt tuning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Wei","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560733"},{"volume-title":"Foundation models for decision making: Problems, methods, and opportunities","year":"2023","author":"Yang","key":"ref37"}],"event":{"name":"2025 IEEE Conference on Games (CoG)","start":{"date-parts":[[2025,8,26]]},"location":"Lisbon, Portugal","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11113832\/11113841\/11114160.pdf?arnumber=11114160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T06:26:36Z","timestamp":1755671196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11114160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/cog64752.2025.11114160","relation":{},"subject":[],"published":{"date-parts":[[2025,8,26]]}}}