{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:47:13Z","timestamp":1755798433260,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"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":[[2024,8,5]]},"DOI":"10.1109\/cog60054.2024.10645565","type":"proceedings-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T18:44:09Z","timestamp":1724870649000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Online Adaptation for Enhancing Imitation Learning Policies"],"prefix":"10.1109","author":[{"given":"Federico","family":"Malato","sequence":"first","affiliation":[{"name":"University of Eastern Finland,School of Computing,Joensuu,Finland"}]},{"given":"Ville","family":"Hautam\u00e4ki","sequence":"additional","affiliation":[{"name":"University of Eastern Finland,School of Computing,Joensuu,Finland"}]}],"member":"263","reference":[{"article-title":"Reinforcement learning: an introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","article-title":"A Brief Survey of Deep Reinforcement Learning","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Processing Magazine, Special Issue on Deep Learning for Image Understanding"},{"key":"ref3","article-title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","author":"Baker","year":"2022","journal-title":"arXiv"},{"article-title":"Mastering Atari with Discrete World Models","volume-title":"International Conference on Learning Representations","author":"Hafner","key":"ref4"},{"article-title":"Mastering Diverse Domains through World Models","year":"2023","author":"Hafner","key":"ref5"},{"article-title":"Deep reinforcement learning from human p","year":"2017","author":"Christiano","key":"ref6"},{"key":"ref7","article-title":"Playing Minecraft with Behavioral Cloning","author":"Kanervisto","year":"2019","journal-title":"NeurIPS Competitions & Demonstrations Track"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231600"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref10","article-title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","author":"Kiran","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref13","article-title":"Imitation Learning: Progress, Taxonomies and Challenges","author":"Zheng","year":"2021","journal-title":"arXiv"},{"key":"ref14","article-title":"Behavioral cloning from observations","author":"Torabi","year":"2018","journal-title":"IJCAI"},{"key":"ref15","article-title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","author":"Arora","year":"2018","journal-title":"arXiv"},{"key":"ref16","first-page":"663","article-title":"Algorithms for Inverse Reinforcement Learning","author":"Ng","year":"2000","journal-title":"ICML \u201800"},{"key":"ref17","article-title":"Generative Adversarial Imitation Learning","author":"Ho","year":"2017","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","author":"Fu","year":"2018","journal-title":"ICLR"},{"key":"ref19","first-page":"2672","article-title":"Generative Adversarial Networks","volume-title":"Proceedings of NeurIPS","author":"Goodfellow"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"article-title":"Attention is All You Need","year":"2017","author":"Vaswani","key":"ref21"},{"key":"ref22","first-page":"13","article-title":"MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned","volume-title":"Proceedings of Machine Learning Research","volume":"176","author":"Kanervisto"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2022.XVIII.010","article-title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","volume-title":"Proceedings of Robotics: Science and Systems","author":"Pari"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447339"},{"article-title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","year":"2022","author":"Fan","key":"ref25"},{"key":"ref26","article-title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","author":"Milani","year":"2023","journal-title":"NeurIPS 2023 Datasets and Benchmarks Oral"},{"article-title":"ChatGPT is not all you need. A State of the Art Review of large Generative AI models","year":"2023","author":"Gozalo-Brizuela","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"article-title":"Proximal policy Optimization Algorithms","year":"2017","author":"Schulman","key":"ref29"},{"key":"ref30","article-title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","author":"Chevalier-Boisvert","year":"2023","journal-title":"in CoRR, abs\/2306.13831"},{"article-title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","year":"2023","author":"Burns","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"event":{"name":"2024 IEEE Conference on Games (CoG)","start":{"date-parts":[[2024,8,5]]},"location":"Milan, Italy","end":{"date-parts":[[2024,8,8]]}},"container-title":["2024 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10645493\/10645533\/10645565.pdf?arnumber=10645565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T10:32:35Z","timestamp":1725013955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cog60054.2024.10645565","relation":{},"subject":[],"published":{"date-parts":[[2024,8,5]]}}}