| dc.contributor | 資科系 | |
| dc.creator (作者) | Liu, Chao-Lin;Chen, Yu-Sheng | |
| dc.creator (作者) | 劉昭麟 | zh_TW |
| dc.date (日期) | 2012-11 | |
| dc.date.accessioned | 22-Jun-2016 17:15:18 (UTC+8) | - |
| dc.date.available | 22-Jun-2016 17:15:18 (UTC+8) | - |
| dc.date.issued (上傳時間) | 22-Jun-2016 17:15:18 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/98238 | - |
| dc.description.abstract (摘要) | Bulls-and-Cows (BAC) is a popular guessing game worldwide. Players try to find opponents` answers via clues provided by the opponents. Some theoretical analyses indicate that, on average, an optimal strategy takes 5.2131 guesses to find the answers for four-digit games. In this paper, alternative methods were explored to realize this theoretical optimality. The methods include a basic filtering method, different ways to recommend the candidate answers, and a machine-learning based method. The best performing combination of non-deterministic methods identified the correct answers with 5.3135 guesses in 504,000 trials. In addition, we were able to find the answers for five-digit and six-digit BAC games with 5.7800 and 6.3999 guesses. | |
| dc.format.extent | 105 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | Proceedings of the 2012 Conference on Technologies and Applications of Artificial Intelligence (TAAI`12), 294‒299. Tainan, Taiwan, 16-18 November 2012 | |
| dc.title (題名) | Toward the optimum performance in the Bulls-and-Cows games | |
| dc.type (資料類型) | conference | |
| dc.identifier.doi (DOI) | 10.1109/TAAI.2012.57 | |
| dc.doi.uri (DOI) | http://dx.doi.org/10.1109/TAAI.2012.57 | |
