Details
| Original language | English |
|---|---|
| Title of host publication | Studies in Fuzziness and Soft Computing |
| Publisher | Springer Science and Business Media Deutschland GmbH |
| Pages | 257-270 |
| Number of pages | 14 |
| Publication status | Published - 27 Oct 2020 |
| Externally published | Yes |
Publication series
| Name | Studies in Fuzziness and Soft Computing |
|---|---|
| Volume | 394 |
| ISSN (Print) | 1434-9922 |
| ISSN (electronic) | 1860-0808 |
Abstract
Computational intelligence agents can reach expert levels in many known games, such as Chess, Go, and Morris. Those systems incorporate powerful machine learning algorithms, which are able to learn from, e.g., observations, play-traces, or by reinforcement learning. While many black box systems, such as deep neural networks, are able to achieve high performance in a wide range of applications, they generally lack interpretability. Additionally, previous systems often focused on a single or a small set of games, which makes it a cumbersome task to rebuild and retrain the agent for each possible application. This paper proposes a method, which extracts an interpretable set of game rules for previously unknown games. Frequent pattern mining is used to find common observation patterns in the game environment. Finally, game rules as well as winning-/losing-conditions are extracted via association rule analysis. Our evaluation shows that a wide range of game rules can be successfully extracted from previously unknown games. We further highlight how the application of fuzzy methods can advance our efforts in generating explainable artifical intelligence (AI) agents.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Science (miscellaneous)
- Mathematics(all)
- Computational Mathematics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Studies in Fuzziness and Soft Computing. Springer Science and Business Media Deutschland GmbH, 2020. p. 257-270 (Studies in Fuzziness and Soft Computing; Vol. 394).
Research output: Chapter in book/report/conference proceeding › Contribution to book/anthology › Research › peer review
}
TY - CHAP
T1 - Association Rule Mining for Unknown Video Games
AU - Dockhorn, Alexander
AU - Saxton, Chris
AU - Kruse, Rudolf
PY - 2020/10/27
Y1 - 2020/10/27
N2 - Computational intelligence agents can reach expert levels in many known games, such as Chess, Go, and Morris. Those systems incorporate powerful machine learning algorithms, which are able to learn from, e.g., observations, play-traces, or by reinforcement learning. While many black box systems, such as deep neural networks, are able to achieve high performance in a wide range of applications, they generally lack interpretability. Additionally, previous systems often focused on a single or a small set of games, which makes it a cumbersome task to rebuild and retrain the agent for each possible application. This paper proposes a method, which extracts an interpretable set of game rules for previously unknown games. Frequent pattern mining is used to find common observation patterns in the game environment. Finally, game rules as well as winning-/losing-conditions are extracted via association rule analysis. Our evaluation shows that a wide range of game rules can be successfully extracted from previously unknown games. We further highlight how the application of fuzzy methods can advance our efforts in generating explainable artifical intelligence (AI) agents.
AB - Computational intelligence agents can reach expert levels in many known games, such as Chess, Go, and Morris. Those systems incorporate powerful machine learning algorithms, which are able to learn from, e.g., observations, play-traces, or by reinforcement learning. While many black box systems, such as deep neural networks, are able to achieve high performance in a wide range of applications, they generally lack interpretability. Additionally, previous systems often focused on a single or a small set of games, which makes it a cumbersome task to rebuild and retrain the agent for each possible application. This paper proposes a method, which extracts an interpretable set of game rules for previously unknown games. Frequent pattern mining is used to find common observation patterns in the game environment. Finally, game rules as well as winning-/losing-conditions are extracted via association rule analysis. Our evaluation shows that a wide range of game rules can be successfully extracted from previously unknown games. We further highlight how the application of fuzzy methods can advance our efforts in generating explainable artifical intelligence (AI) agents.
UR - http://www.scopus.com/inward/record.url?scp=85094557810&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-54341-9_22
DO - 10.1007/978-3-030-54341-9_22
M3 - Contribution to book/anthology
AN - SCOPUS:85094557810
T3 - Studies in Fuzziness and Soft Computing
SP - 257
EP - 270
BT - Studies in Fuzziness and Soft Computing
PB - Springer Science and Business Media Deutschland GmbH
ER -