{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:48:45Z","timestamp":1755798525667,"version":"3.28.0"},"reference-count":34,"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\/cog57401.2023.10333201","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":2,"title":["Learning Computational Efficient Bots with Costly Features"],"prefix":"10.1109","author":[{"given":"Anthony","family":"Kobanda","sequence":"first","affiliation":[{"name":"Ubisoft La Forge Ubisoft,Bordeaux,France"}]},{"given":"Valliappan","family":"C. A.","sequence":"additional","affiliation":[{"name":"Ubisoft La Forge Ubisoft,Montréal,Canada"}]},{"given":"Joshua","family":"Romoff","sequence":"additional","affiliation":[{"name":"Ubisoft La Forge Ubisoft,Montréal,Canada"}]},{"given":"Ludovic","family":"Denoyer","sequence":"additional","affiliation":[{"name":"Ubisoft La Forge Ubisoft,Bordeaux,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1887\/0750308958"},{"key":"ref2","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Chen","year":"2021"},{"key":"ref3","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref5","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"CoRR"},{"article-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref6"},{"key":"ref7","article-title":"Graph augmented deep reinforcement learning in the gamerland3d environment","volume":"abs\/2112.11731","author":"Beeching","year":"2021","journal-title":"CoRR"},{"key":"ref8","article-title":"Offline reinforcement learning with implicit q-learning","volume":"abs\/2110.06169","author":"Kostrikov","year":"2021","journal-title":"CoRR"},{"key":"ref9","article-title":"Simplified 3D movement and pathfinding using navigation meshes","volume-title":"Game Programming Gems","author":"Snook","year":"2000"},{"key":"ref10","article-title":"Deep reinforcement learning for navigation in AAA video games","volume":"abs\/2011.04764","author":"Alonso","year":"2020","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553463"},{"article-title":"Opportunistic learning: Budgeted cost-sensitive learning from data streams","year":"2019","author":"Kachuee","key":"ref12"},{"article-title":"Online budgeted learning for classifier induction","year":"2019","author":"Fainman","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013959"},{"article-title":"Budgeted learning of naive-bayes classifiers","year":"2012","author":"Lizotte","key":"ref15"},{"article-title":"Feature selection using reinforcement learning","year":"2021","author":"Rasoul","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46349-0_25"},{"article-title":"Efficient neural architecture search with performance prediction","year":"2021","author":"Alshubaily","key":"ref18"},{"article-title":"Improving the sample-efficiency of neural architecture search with reinforcement learning","year":"2021","author":"Nagy","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80126-7_42"},{"key":"ref21","article-title":"Learning time-efficient deep architectures with budgeted super networks","volume":"abs\/1706.00046","author":"Veniat","year":"2017","journal-title":"CoRR"},{"key":"ref22","article-title":"Stochastic adaptive neural architecture search for keyword spotting","author":"V\u00e9niat","year":"2018","journal-title":"CoRR"},{"article-title":"Neural architecture search with reinforcement learning","year":"2016","author":"Zoph","key":"ref23"},{"key":"ref24","first-page":"498","article-title":"Online feature selection for model-based reinforcement learning","volume-title":"Proceedings of the 30th International Conference on Machine Learning","volume":"28","author":"Nguyen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89722-4_10"},{"article-title":"Memory-based control with recurrent neural networks","year":"2015","author":"Heess","key":"ref26"},{"article-title":"Adaptive transformers in rl","year":"2020","author":"Kumar","key":"ref27"},{"key":"ref28","first-page":"27921","article-title":"Multi-game decision transformers","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Lee","year":"2022"},{"key":"ref29","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"International conference on machine learning","author":"Parisotto"},{"key":"ref30","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Active reinforcement learning: Observing rewards at a cost","volume":"abs\/2011.06709","author":"Krueger","year":"2020","journal-title":"CoRR"},{"key":"ref32","article-title":"Reinforcement learning with state observation costs in action-contingent noiselessly observable markov decision processes","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Nam","year":"2021"},{"key":"ref33","article-title":"Reinforcement learning with efficient active feature acquisition","volume":"abs\/2011.00825","author":"Yin","year":"2020","journal-title":"CoRR"},{"key":"ref34","article-title":"Deep reinforcement learning for cost-effective medical diagnosis","volume":"abs\/2302.10261","author":"Yu","year":"2023","journal-title":"CoRR"}],"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\/10333201.pdf?arnumber=10333201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T18:43:02Z","timestamp":1707244982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333201","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}