Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Per-Arne Andersen"'
Publikováno v:
Applied Sciences, Vol 12, Iss 17, p 8534 (2022)
This paper presents a novel approach to training a real-world object detection system based on synthetic data utilizing state-of-the-art technologies. Training an object detection system can be challenging and time-consuming as machine learning requi
Externí odkaz:
https://doaj.org/article/47370d84f7aa4a19b125b9eaa6e38354
Publikováno v:
IFIP Advances in Information and Communication Technology ISBN: 9783031341106
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6fcf9f91ba257b8082bd0ac5962476bb
https://doi.org/10.1007/978-3-031-34111-3_8
https://doi.org/10.1007/978-3-031-34111-3_8
Publikováno v:
IEEE Transactions on Systems, Man & Cybernetics: Systems
We focus on the important problem of emergency evacuation, which clearly could benefit from reinforcement learning that has been largely unaddressed. Emergency evacuation is a complex task which is difficult to solve with reinforcement learning, sinc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a80ac219f795346cbb3736c7470a28b
https://doi.org/10.1109/tsmc.2020.2967936
https://doi.org/10.1109/tsmc.2020.2967936
This paper addresses the dire need for a platform that efficiently provides a framework for running reinforcement learning (RL) experiments. We propose the CaiRL Environment Toolkit as an efficient, compatible, and more sustainable alternative for tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0b0e8567257f8211eeba10f49ce581b
http://arxiv.org/abs/2210.01235
http://arxiv.org/abs/2210.01235
Publikováno v:
Information Sciences
Reinforcement learning has shown to be profoundly successful at learning optimal policies for simulated environments using distributed training with extensive compute capacity. Model-free reinforcement learning uses the notion of trial and error, whe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8de0a3991ada7de9317c4d44790f8c5f
https://doi.org/10.1016/j.ins.2020.06.010
https://doi.org/10.1016/j.ins.2020.06.010
Autor:
Sander Jyhne, Morten Goodwin, Per-Arne Andersen, Ivar Oveland, Alexander Salveson Nossum, Mathilde Ørstavik, Karianne Ormseth, Andrew Flatman
Publikováno v:
Nordic Machine Intelligence (NMI)
MapAI: Precision in Building Segmentation is a competition arranged with the Norwegian Artificial Intelligence Research Consortium (NORA) in collaboration with Centre for Artificial Intelligence Research at the University of Agder (CAIR), the Norwegi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1431eb0d1b4a34fb3ae0633932156171
https://hdl.handle.net/11250/3048544
https://hdl.handle.net/11250/3048544
Publikováno v:
Artificial Intelligence XXXIX ISBN: 9783031214400
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::258175798620063287ea8739a5821012
https://doi.org/10.1007/978-3-031-21441-7_14
https://doi.org/10.1007/978-3-031-21441-7_14
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030910990
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7287651fb9f7606299b0f156ae940e6
https://doi.org/10.1007/978-3-030-91100-3_4
https://doi.org/10.1007/978-3-030-91100-3_4
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030717100
Deep Reinforcement Learning (RL) is unquestionably a robust framework to train autonomous agents in a wide variety of disciplines. However, traditional deep and shallow model-free RL algorithms suffer from low sample efficiency and inadequate general
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::faf8aa580e8fc97818e6b4516f793444
https://doi.org/10.1007/978-3-030-71711-7_11
https://doi.org/10.1007/978-3-030-71711-7_11
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030637989
SGAI Conf.
SGAI Conf.
Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5275fb363d63bf5e8e2cbe79c8167474
https://doi.org/10.1007/978-3-030-63799-6_7
https://doi.org/10.1007/978-3-030-63799-6_7