{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T10:35:02Z","timestamp":1790246102310,"version":"4.1.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"joint French\/Canadian call by ANR & NSERC","doi-asserted-by":"publisher","award":["ANR-15-CE23-0029,STPGP479356-15"],"award-info":[{"award-number":["ANR-15-CE23-0029,STPGP479356-15"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012681","name":"CNRS\/IN2P3 Computing Center","doi-asserted-by":"publisher","award":["CNRS\/IN2P3"],"award-info":[{"award-number":["CNRS\/IN2P3"]}],"id":[{"id":"10.13039\/100012681","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412212","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"158-165","source":"Crossref","is-referenced-by-count":5,"title":["Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer"],"prefix":"10.1109","author":[{"given":"Edward","family":"Beeching","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilles","family":"Debangoye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Simonin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref38","article-title":"Scalable trustregion method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"2017","journal-title":"NIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv pre-print"},{"key":"ref31","author":"schaarschmidt","year":"2017","journal-title":"Tensorforce A tensorflow library for applied reinforcement learning"},{"key":"ref30","article-title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","author":"savva","year":"2017","journal-title":"ArXiv pre-print"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient following algorithms for connectionist reinforcement learning","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref36","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"ArXiv pre-print"},{"key":"ref35","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref34","article-title":"Accelerated methods for deep reinforcement learning","author":"stooke","year":"2018","journal-title":"ArXiv pre-print"},{"key":"ref10","first-page":"2, 3, 4","article-title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","author":"espeholt","year":"2018","journal-title":"ICML"},{"key":"ref40","article-title":"A study on overfitting in deep reinforcement learning","author":"zhang","year":"2018","journal-title":"ArXiv"},{"key":"ref11","first-page":"3","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"AAAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","first-page":"2","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"ICLRE"},{"key":"ref14","article-title":"Navigation and planning in latent maps","author":"kayalibay","year":"0","journal-title":"FAIM Workshop on Prediction and Generative Modeling in Reinforcement Learning"},{"key":"ref15","first-page":"2, 3,4","article-title":"ViZ- Doom: A Doom-based AI research platform for visual reinforcement learning","author":"kempka","year":"0","journal-title":"IEEE Conference on Computatonal Intelligence and Games CIG"},{"key":"ref16","article-title":"AI2-THOR: An Interactive 3D Environment for Visual AI","author":"kolve","year":"2017","journal-title":"ArXiv"},{"key":"ref17","author":"kostrikov","year":"2018","journal-title":"Pytorch implementations of reinforcement learning algorithms"},{"key":"ref18","article-title":"Playing FPS games with deep reinforcement learning","author":"lample","year":"2017","journal-title":"AAAI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref28","article-title":"OpenAI","year":"2018","journal-title":"Openai five"},{"key":"ref4","first-page":"2. 3","article-title":"HoME: a Household Multimodal Environment","author":"brodeur","year":"2018","journal-title":"ICLRE"},{"key":"ref27","article-title":"Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications","author":"m\u00fcller","year":"2017","journal-title":"ArXiv"},{"key":"ref3","first-page":"2","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"arxiv pre-print 1606 01540"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094648"},{"key":"ref29","article-title":"Neural map: Structured memory for deep reinforcement learning","author":"parisotto","year":"2017","journal-title":"ArXiv pre-print"},{"key":"ref5","first-page":"2","article-title":"Gated Feedback Recurrent Neural Networks","author":"chung","year":"2015","journal-title":"ICML"},{"key":"ref8","first-page":"3","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines"},{"key":"ref7","first-page":"1","article-title":"Neural Modular Control for Embodied Question Answering","author":"das","year":"2018","journal-title":"CVPR"},{"key":"ref2","first-page":"2,3","article-title":"DeepMind Lab","author":"beattie","year":"2016","journal-title":"ArXiv pre-print"},{"key":"ref9","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"CoRL"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref20","first-page":"1","article-title":"End-to-End Training of Deep Visuomotor Policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref21","article-title":"Continuous Control with Deep Reinforcement Learning","author":"lillicrap","year":"2015","journal-title":"ArXiv pre-print"},{"key":"ref24","author":"mnih","year":"2016","journal-title":"Asynchronous methods for deep reinforcement learning"},{"key":"ref23","article-title":"Learning to Navigate in Complex Environments","author":"mirowski","year":"2017","journal-title":"ICLRE"},{"key":"ref26","article-title":"Ray: A Distributed Framework for Emerging AI Applications","author":"moritz","year":"0","journal-title":"USENIX Symposium on Operating Systems Design and Implementation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412212.pdf?arnumber=9412212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:52Z","timestamp":1652197252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412212","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}