Solving the Rubik's Cube with Learned Guidance Functions

被引：0

作者：

Johnson, Colin G. ^{[1
]}

机构：

[1] Univ Kent, Sch Comp, Canterbury, Kent, England

来源：

2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI) | 2018年

关键词：

Machine learning; error measures; loss functions; fitness landscapes; human-like computing; GAME;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper introduces move sequence problems-problems where a system can exist in a number of states, including a goal slate, with moves between those slates. This paper introduces Learned Guidance Functions (LGFs) as a machine learning method to tackle these. An LGF is a function learned by supervised machine learning that predicts how far a particular state is from the goal state. These methods are applied to the challenging problem of unscrambling a Rubik's Cube.

引用

页码：2082 / 2089

页数：8

共 50 条

[1] Augmented Reality Based Guidance for Solving Rubik's Cube Using HMD
Park, Jaebum
Park, Changhoon
HCI INTERNATIONAL 2016 - POSTERS' EXTENDED ABSTRACTS, PT II, 2016, 618 : 524 - 529
[2] CUBOT, A ROBOT FOR SOLVING RUBIK'S CUBE.
Dyer, R.D.
Hartman, J.S.
Kelley, R.C.
Technical Paper - Society of Manufacturing Engineers, 1984,
[3] Solving the Rubik's cube with stepwise deep learning
Johnson, Colin G.
EXPERT SYSTEMS, 2021, 38 (03)
[4] Solving Rubik's Cube: Disk is the new RAM
Kunkle, Daniel
Cooperman, Gene
COMMUNICATIONS OF THE ACM, 2008, 51 (04) : 31 - 33
[5] Solving the Rubik's cube with deep reinforcement learning and search
Agostinelli, Forest
McAleer, Stephen
Shmakov, Alexander
Baldi, Pierre
NATURE MACHINE INTELLIGENCE, 2019, 1 (08) : 356 - 363
[6] Solving the Rubik’s cube with deep reinforcement learning and search
Forest Agostinelli
Stephen McAleer
Alexander Shmakov
Pierre Baldi
Nature Machine Intelligence, 2019, 1 : 356 - 363
[7] Solving the Rubik's Cube Optimally is NP-complete
Demaine, Erik D.
Eisenstat, Sarah
Rudoy, Mikhail
35TH SYMPOSIUM ON THEORETICAL ASPECTS OF COMPUTER SCIENCE (STACS 2018), 2018, 96
[8] Automatic System for Learning the Process of Solving Rubik's Cube
Sosdean, Lucian
Stanciu, Loredana
Albu, Adriana
18TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS, SACI 2024, 2024, : 473 - 476
[9] An Evolutionary Approach for Solving the Rubik's Cube Incorporating Exact Methods
El-Sourani, Nail
Hauke, Sascha
Borschbach, Markus
APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS, 2010, 6024 : 80 - 89
[10] Design and Comparison of two Evolutionary Approaches for Solving the Rubik's Cube
El-Sourani, Nail
Borschbach, Markus
PARALLEL PROBLEM SOLVING FROM NATURE-PPSN XI, PT II, 2010, 6239 : 442 - 451

← 1 2 3 4 5 →