{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:45:50Z","timestamp":1765547150077,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"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":[[2023,8,21]]},"DOI":"10.1109\/cog57401.2023.10333234","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T18:48:21Z","timestamp":1701715701000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning"],"prefix":"10.1109","author":[{"given":"Alessandro","family":"Sestini","sequence":"first","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Joakim","family":"Bergdahl","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Konrad","family":"Tollmar","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Andrew D.","family":"Bagdanov","sequence":"additional","affiliation":[{"name":"Università Degli Studi di Firenze"}]},{"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\/3410404.3414249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3524494.3527627"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619053"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3226910"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619048"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"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","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848057"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MODELS.2015.7338274"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SBGAMES.2018.00015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3313039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2013.6693143"},{"article-title":"Software testing by active learning for commercial games","volume-title":"Conference on Artificial Intelligence (AAAI)","author":"Xiao","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00077"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231915"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231552"},{"volume-title":"Faulty reward functions in the wild","year":"2016","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848091"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2020.2990865"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490398"},{"article-title":"Quickly training game-playing agents with machine learning","year":"2021","author":"Haller","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2018.8477829"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref23"},{"issue":"6","key":"ref24","first-page":"689","article-title":"Sur la distance de deux lois de probabilit\u00e9","volume":"244","author":"Fr\u00e9chet","year":"1957","journal-title":"Comptes Rendus Hebdomadaires des Seances de L Academie des Sciences"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7415"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/294"},{"journal-title":"Adversarial attacks on neural network policies","year":"2017","author":"Huang","key":"ref27"},{"article-title":"Generative adversarial imitation learning","volume-title":"Proceedings of the 30st International Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho","key":"ref28"},{"article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Fu","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207672"},{"article-title":"S4RL: Surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Conference on Robot Learning (CORL)","author":"Sinha","key":"ref32"},{"key":"ref33","article-title":"A minimalist approach to offline reinforcement learning","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cog52621.2021.9619127"},{"journal-title":"Direct behavior specification via constrained reinforcement learning","year":"2021","author":"Roy","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9618983"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"article-title":"Exploration by random network distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Burda","key":"ref38"},{"journal-title":"Explainable artificial intelligence (XAI) for increasing user trust in deep reinforcement learning driven autonomous systems","year":"2021","author":"Druce","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2013.02.002"},{"key":"ref41","article-title":"One-shot imitation learning","author":"Duan","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"journal-title":"Hierarchical few-shot imitation with skill transition models","year":"2021","author":"Hakhamaneshi","key":"ref42"},{"key":"ref43","article-title":"Conservative Q-learning for offline reinforcement learning","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref44","article-title":"Decision transformer: Reinforcement learning via sequence modeling","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"article-title":"Coordinated multi-agent imitation learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Le","key":"ref45"}],"event":{"name":"2023 IEEE Conference on Games (CoG)","start":{"date-parts":[[2023,8,21]]},"location":"Boston, MA, USA","end":{"date-parts":[[2023,8,24]]}},"container-title":["2023 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10333091\/10333129\/10333234.pdf?arnumber=10333234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T18:33:45Z","timestamp":1707330825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333234\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333234","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}