An Agent for EinStein Würfelt Nicht! Using N-Tuple Networks

Yeong Jia Roger Chu, Yuan Hao Chen, Chu Hsuan Hsueh, I-Chen Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes the implemention of an agent that plays EinStein würfelt nich!. The agent is based on the common Monte-Carlo tree search (MCTS) which is especially good at dealing with the randomness in a game. For the agent, this paper proposes to use n-tuple networks trained by Monte-Carlo learning. In the agent, the trained n-tuple networks is used together with MCTS by the following three approaches: progressive bias, prior knowledge and ϵ-greedy. The experimental results show that ϵ-greedy improved the playing strength the most, which obtained a win rate of 61.05% against the baseline agent. By combining all three approaches, the win rate increased a little to 62.25%. And the enhanced agent tournament in Computer Olympaid 2017.

Original languageEnglish
Title of host publicationProceedings - 2017 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages184-189
Number of pages6
ISBN (Electronic)9781538642030
DOIs
StatePublished - 9 May 2018
Event2017 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2017 - Taipei, Taiwan
Duration: 1 Dec 20173 Dec 2017

Publication series

NameProceedings - 2017 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2017

Conference

Conference2017 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2017
CountryTaiwan
CityTaipei
Period1/12/173/12/17

Cite this

Chu, Y. J. R., Chen, Y. H., Hsueh, C. H., & Wu, I-C. (2018). An Agent for EinStein Würfelt Nicht! Using N-Tuple Networks. In Proceedings - 2017 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2017 (pp. 184-189). (Proceedings - 2017 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TAAI.2017.32