Zobrazeno 1 - 10 of 59 pro vyhledávání: '"Kee-Eung Kim"'
1
Data Augmentation for Learning to Play in Text-Based Games
Autor: Jinhyeon Kim, Kee-Eung Kim
Publikováno v: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.
Improving generalization in text-based games serves as a useful stepping-stone towards reinforcement learning (RL) agents with generic linguistic ability. Data augmentation for generalization in RL has shown to be very successful in classic control a
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::39f2fa6dd433147d296ba08fa1b67f17
https://doi.org/10.24963/ijcai.2022/436
Zobrazit plný text záznamu
2
Layered Behavior Modeling via Combining Descriptive and Prescriptive Approaches: A Case Study of Infantry Company Engagement
Autor: Il-Chul Moon, Junseok Lee, Jang Won Bae, Do-Hyung Kim, Kanghoon Lee, Jongmin Lee, Kee-Eung Kim
Publikováno v: IEEE Transactions on Systems, Man, and Cybernetics: Systems. 50:2551-2565
Defense modeling and simulation (DMS and prescriptive modeling to discover best individual actions in the reduced space. For the generalization, the proposed method adapts both modeling methods being modularized, and then the proposed method suggeste
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0c74440feda257affabb2bb0f5c0d087
https://doi.org/10.1109/tsmc.2018.2822312
Zobrazit plný text záznamu
3
Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented Dialogues
Autor: Jongmin Lee, Kee-Eung Kim, Youngsoo Jang
Publikováno v: AAAI
We consider a strategic dialogue task, where the ability to infer the other agent's goal is critical to the success of the conversational agent. While this problem can be naturally formulated as Bayesian planning, it is known to be a very difficult p
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fe14467d493de06513a607759c52eb1f
https://doi.org/10.1609/aaai.v34i05.6308
Zobrazit plný text záznamu
4
Monte-Carlo Tree Search in Continuous Action Spaces with Value Gradients
Autor: Geon-Hyeong Kim, Kee-Eung Kim, Wonseok Jeon, Jongmin Lee
Publikováno v: AAAI
Monte-Carlo Tree Search (MCTS) is the state-of-the-art online planning algorithm for large problems with discrete action spaces. However, many real-world problems involve continuous action spaces, where MCTS is not as effective as in discrete action
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2c7acd32510bd515f457662fd8ffc87e
https://doi.org/10.1609/aaai.v34i04.5885
Zobrazit plný text záznamu
10
An Improved Particle Filter With a Novel Hybrid Proposal Distribution for Quantitative Analysis of Gold Immunochromatographic Strips
Autor: Zidong Wang, Nianyin Zeng, Hong Zhang, Yurong Li, Xiaohui Liu, Kee-Eung Kim
Publikováno v: IEEE Transactions on Nanotechnology. 18:819-829
In this paper, a novel statistical pattern recognition method is proposed for accurately segmenting test and control lines from the gold immunochromatographic strip (GICS) images for the benefits of quantitative analysis. A new dynamic state-space mo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::302c451376dcc453c0373f9defd01268
https://doi.org/10.1109/tnano.2019.2932271
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje