Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chu, Yeong-Jia Roger | en_US |
dc.contributor.author | Chen, Yuan-Hao | en_US |
dc.contributor.author | Hsueh, Chu-Hsuan | en_US |
dc.contributor.author | Wu, I-Chen | en_US |
dc.date.accessioned | 2018-08-21T05:56:24Z | - |
dc.date.available | 2018-08-21T05:56:24Z | - |
dc.date.issued | 2017-01-01 | en_US |
dc.identifier.issn | 2376-6816 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/146168 | - |
dc.description.abstract | This paper describes the implementation of an agent that plays EinStein wurfelt nicht!. 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 network is used together with MCTS by the following three approaches: progressive bias, prior knowledge and c-greedy. The experimental results show that epsilon-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 also won the first place in the EinStein wurfelt nicht! tournament in Computer Olympiad 2017. | en_US |
dc.language.iso | en_US | en_US |
dc.title | An Agent for EinStein Wurfelt Nicht! Using N-Tuple Networks | en_US |
dc.type | Proceedings Paper | en_US |
dc.identifier.journal | 2017 CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI) | en_US |
dc.citation.spage | 184 | en_US |
dc.citation.epage | 189 | en_US |
dc.contributor.department | 資訊工程學系 | zh_TW |
dc.contributor.department | Department of Computer Science | en_US |
dc.identifier.wosnumber | WOS:000434087700040 | en_US |
Appears in Collections: | Conferences Paper |