Výsledky vyhledávání - "Kokolo Ikeda"

Akademický článek

Analyses of Tabular AlphaZero on Strongly-Solved Stochastic Games

Autor: Chu-Hsuan Hsueh, Kokolo Ikeda, I-Chen Wu, Jr-Chang Chen, Tsan-Sheng Hsu

Publikováno v: IEEE Access, Vol 11, Pp 18157-18182 (2023)

The AlphaZero algorithm achieved superhuman levels of play in chess, shogi, and Go by learning without domain-specific knowledge except for game rules. This paper targets stochastic games and investigates whether AlphaZero can learn theoretical value

Externí odkaz: https://doaj.org/article/c193262045494c36be6111ffd6a24b4e

Zobrazit plný text záznamu

Generation of Game Stages with Quality and Diversity by Reinforcement Learning in Turn-based RPG

Autor: Kokolo Ikeda, Chu-Hsuan Hsueh, Sang-Gyu Nam

Publikováno v: IEEE Transactions on Games (ToG). 14(3):488-501

Many recent studies in procedural content generation (PCG) are based on machine learning. One of the promising approaches is generative models, which have shown impressive results in generating new pictures and videos from existing ones. However, it

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83cfec54ab895a05368622cd2218f36f
http://hdl.handle.net/10119/18245

Zobrazit plný text záznamu

Graph Convolutional Networks for Turn-Based Strategy Games

Autor: Wanxiang Li, Houkuan He, Chu-Hsuan Hsueh, Kokolo Ikeda

Publikováno v: Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022). 2:552-561

In this paper, we research Turn-Based Strategy (TBS) games that allow players to move multiple pieces in one turn and have multiple initial states. Compared to a game like Chess, which allows only one piece to move per turn and has a single initial s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a53383a3849f41c567afad9c56ac118b
http://hdl.handle.net/10119/18242

Zobrazit plný text záznamu

Improving the Human-Likeness of Game AI’s Moves by Combining Multiple Prediction Models

Autor: Tatsuyoshi Ogawa, Chu-Hsuan Hsueh, Kokolo Ikeda

Publikováno v: Proceedings of the 15th International Conference on Agents and Artificial Intelligence.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9a393f7c355d29b22feceeff2c4f9b3d
https://doi.org/10.5220/0011804200003393

Zobrazit plný text záznamu

An Efficient Aircraft Boarding Strategy Considering Implementation

Autor: Kenji Uehara, Kunihiko Hiraishi, Kokolo Ikeda

Publikováno v: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. :1051-1058

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8c8d8e51d6b1eadf572677a0c84a7c41
https://doi.org/10.1587/transfun.2020eap1077

Zobrazit plný text záznamu

Procedural Maze Generation Considering Difficulty from Human Players’ Perspectives

Autor: Keita Fujihira, Chu-Hsuan Hsueh, Kokolo Ikeda

Publikováno v: Lecture Notes in Computer Science ISBN: 9783031114878

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e4555dca8b76eb954c45e042251d5c64
https://doi.org/10.1007/978-3-031-11488-5_15

Zobrazit plný text záznamu

Procedural Content Generation of Rhythm Games Using Deep Learning Methods

Autor: Kokolo Ikeda, Wanxiang Li, Yubin Liang

Publikováno v: Entertainment Computing and Serious Games ISBN: 9783030346430
ICEC-JCSG

The rhythm game is a type of video game which is popular to many people. But the game contents (required action and its timing) of rhythm game are usually hand-crafted by human designers. In this research, we proposed an automatic generation method t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::255b2ce72b8842101e120a13a4967d0b
http://hdl.handle.net/10119/18205

Zobrazit plný text záznamu

Analyses of Tabular AlphaZero on NoGo

Autor: Kokolo Ikeda, Sang-Gyu Nam, Chu-Hsuan Hsueh, I-Chen Wu

Publikováno v: TAAI

The AlphaZero algorithm has been shown to achieve superhuman levels of plays in chess, shogi, and Go. This paper presents analytic investigations of the algorithm on NoGo, a variant of Go that players cannot capture the opponents’ stones. More spec

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f22e9ebc2261bbf3550dcfa2ee025092
http://hdl.handle.net/10119/18244

Zobrazit plný text záznamu

Designing Policy Network with Deep Learning in Turn-Based Strategy Games

Autor: Kokolo Ikeda, Tomihiro Kimura

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030658823
ACG

Research on artificial intelligence (AI) has experienced a substantial stride since the advent of the AlphaGo, progressing the application of deep learning techniques for the game application. However, significant research is still unpublished in the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f0c16299ae12d61529067af174a664fd
https://doi.org/10.1007/978-3-030-65883-0_12

Zobrazit plný text záznamu

Improving Human Players’ T-Spin Skills in Tetris with Procedural Problem Generation

Autor: Chu-Hsuan Hsueh, Kokolo Ikeda, Taishi Oikawa

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030658823
ACG

Researchers in the field of computer games interest in creating not only strong game-playing programs, but also programs that can entertain or teach human players. One of the branches is procedural content generation, aiming to generate game contents

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d1d47b5879009a252f61fe6f5f8a5e01
https://doi.org/10.1007/978-3-030-65883-0_4

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání