An architecture-Algorithm co-design of artificial intelligence for Trax player

Qing Lu; Chiu Wing Sham; Chung Ming Lau

doi:10.1109/FPT.2015.7393120

An architecture-Algorithm co-design of artificial intelligence for Trax player

Qing Lu
, Chiu Wing Sham
, Chung Ming Lau

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

Trax is a two-player game of simple rules but strategic depth. This article proposes an FPGA-based artificial intelligence for its endless version called Supertrax. An implementable algorithm is developed by combining several strategies and techniques functioning at various levels of software and hardware. These methods are developed using heuristics, multi-level pattern recognition, Monte-Carlo Tree Search, and path-based scheduling. A specific architecture has also been described to accommodate this algorithm. The proposal contributes a novel idea on this subject and its performance will be shown in the design competition to be held in FPT'15.

Original language	English
Title of host publication	2015 International Conference on Field Programmable Technology, FPT 2015
Publisher	IEEE
Pages	264-267
Number of pages	4
ISBN (Electronic)	9781467390910
DOIs	https://doi.org/10.1109/FPT.2015.7393120
Publication status	Published - 25 Jan 2016
Event	International Conference on Field Programmable Technology, FPT 2015 - Queenstown, New Zealand Duration: 7 Dec 2015 → 9 Dec 2015

Conference

Conference	International Conference on Field Programmable Technology, FPT 2015
Country/Territory	New Zealand
City	Queenstown
Period	7/12/15 → 9/12/15

ASJC Scopus subject areas

Computer Science Applications
Hardware and Architecture
Software

More information

10.1109/FPT.2015.7393120

Cite this

@inproceedings{cbfd9c18763949df90f8646f1cc706ad,

title = "An architecture-Algorithm co-design of artificial intelligence for Trax player",

abstract = "Trax is a two-player game of simple rules but strategic depth. This article proposes an FPGA-based artificial intelligence for its endless version called Supertrax. An implementable algorithm is developed by combining several strategies and techniques functioning at various levels of software and hardware. These methods are developed using heuristics, multi-level pattern recognition, Monte-Carlo Tree Search, and path-based scheduling. A specific architecture has also been described to accommodate this algorithm. The proposal contributes a novel idea on this subject and its performance will be shown in the design competition to be held in FPT'15.",

author = "Qing Lu and Sham, \{Chiu Wing\} and Lau, \{Chung Ming\}",

year = "2016",

month = jan,

day = "25",

doi = "10.1109/FPT.2015.7393120",

language = "English",

pages = "264--267",

booktitle = "2015 International Conference on Field Programmable Technology, FPT 2015",

publisher = "IEEE",

address = "United States",

note = "International Conference on Field Programmable Technology, FPT 2015 ; Conference date: 07-12-2015 Through 09-12-2015",

}

An architecture-Algorithm co-design of artificial intelligence for Trax player. / Lu, Qing; Sham, Chiu Wing; Lau, Chung Ming.
2015 International Conference on Field Programmable Technology, FPT 2015. IEEE, 2016. p. 264-267 7393120.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - An architecture-Algorithm co-design of artificial intelligence for Trax player

AU - Lu, Qing

AU - Sham, Chiu Wing

AU - Lau, Chung Ming

PY - 2016/1/25

Y1 - 2016/1/25

N2 - Trax is a two-player game of simple rules but strategic depth. This article proposes an FPGA-based artificial intelligence for its endless version called Supertrax. An implementable algorithm is developed by combining several strategies and techniques functioning at various levels of software and hardware. These methods are developed using heuristics, multi-level pattern recognition, Monte-Carlo Tree Search, and path-based scheduling. A specific architecture has also been described to accommodate this algorithm. The proposal contributes a novel idea on this subject and its performance will be shown in the design competition to be held in FPT'15.

AB - Trax is a two-player game of simple rules but strategic depth. This article proposes an FPGA-based artificial intelligence for its endless version called Supertrax. An implementable algorithm is developed by combining several strategies and techniques functioning at various levels of software and hardware. These methods are developed using heuristics, multi-level pattern recognition, Monte-Carlo Tree Search, and path-based scheduling. A specific architecture has also been described to accommodate this algorithm. The proposal contributes a novel idea on this subject and its performance will be shown in the design competition to be held in FPT'15.

UR - https://www.scopus.com/pages/publications/84963593315

U2 - 10.1109/FPT.2015.7393120

DO - 10.1109/FPT.2015.7393120

M3 - Conference article published in proceeding or book

SP - 264

EP - 267

BT - 2015 International Conference on Field Programmable Technology, FPT 2015

PB - IEEE

T2 - International Conference on Field Programmable Technology, FPT 2015

Y2 - 7 December 2015 through 9 December 2015

ER -

An architecture-Algorithm co-design of artificial intelligence for Trax player

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this