Zobrazeno 1 - 10
of 134
pro vyhledávání: '"Aske Plaat"'
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization are reinforcement learning and planning, which both largely hav
Externí odkaz:
https://doaj.org/article/1964865081014a27b68c9d4d7dda37c8
Publikováno v:
International Journal of Serious Games, Vol 3, Iss 3 (2016)
Gameplay is commonly considered to be a voluntary activity. Game designers generally believe that voluntary gameplay is essentially different from mandatory gameplay. Such a belief may be a challenge for serious games, as instruction is usually manda
Externí odkaz:
https://doaj.org/article/48296bd1e43643a09f9c066265ccff03
Publikováno v:
Machine Learning. 111:3227-3244
Meta-learning can be used to learn a good prior that facilitates quick learning; two popular approaches are MAML and the meta-learner LSTM. These two methods represent important and different approaches in meta-learning. In this work, we study the tw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1f09cc43635e635941939186ebc5ac16
https://doi.org/10.1007/s10994-022-06210-y
https://doi.org/10.1007/s10994-022-06210-y
Publikováno v:
ACM Proceedings on Human-Computer Interaction, 5(CHIPLAY)
Video games frequently feature 'open world' environments, designed to motivate exploration. Level design patterns are implemented to invoke curiosity and to guide player behavior. However, evidence of the efficacy of such patterns has remained theore
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::98bbc452bb0c99e405f14631c5dc4546
https://doi.org/10.1145/3474698
https://doi.org/10.1145/3474698
Publikováno v:
International Journal of Information Technology & Decision Making. WORLD SCIENTIFIC PUBL CO PTE LTD
International Journal of Information Technology & Decision Making
International Journal of Information Technology & Decision Making
The landmark achievements of AlphaGo Zero have created great research interest into self-play in reinforcement learning. In self-play, Monte Carlo Tree Search (MCTS) is used to train a deep neural network, which is then used itself in tree searches.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0439a4710c3abcf1b9a66a73c2fb8989
http://hdl.handle.net/1887/3502407
http://hdl.handle.net/1887/3502407
Publikováno v:
2022 IEEE Conference on Games (CoG).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92d659a759958c41599f5b435326d501
https://doi.org/10.1109/cog51982.2022.9893715
https://doi.org/10.1109/cog51982.2022.9893715
Autor:
Aske Plaat
Publikováno v:
Deep Reinforcement Learning ISBN: 9789811906374
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc71d9e46a1044560d402c2b22a1562e
https://doi.org/10.1007/978-981-19-0638-1_3
https://doi.org/10.1007/978-981-19-0638-1_3
Autor:
Aske Plaat
Publikováno v:
Deep Reinforcement Learning ISBN: 9789811906374
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a3ff25db482eb86af5e8dd62272d4c67
https://doi.org/10.1007/978-981-19-0638-1_7
https://doi.org/10.1007/978-981-19-0638-1_7
Autor:
Aske Plaat
Publikováno v:
Deep Reinforcement Learning ISBN: 9789811906374
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::55942c3a7c3137cdac687401bbd838dc
https://doi.org/10.1007/978-981-19-0638-1_6
https://doi.org/10.1007/978-981-19-0638-1_6