APPROBATION OF DETECTED WEAKNESS OF SELF-TAUGHT GO GAME AI KATAGO
Authors:
1.
Moskovskiy gosudarstvennyy universitet imeni M.V. Lomonosova
from 01.01.2023 until now Russian Federation
from 01.01.2023 until now Russian Federation
2.
Moskovskiy gosudarstvennyy universitet imeni M.V. Lomonosova
from 01.01.2006 to 01.01.2011 Russian Federation
from 01.01.2006 to 01.01.2011 Russian Federation
Type:
Сonference abstract
Published:
08.02.2024
Subject area:
VAK Russia 5.8.4
VAK Russia 5.8.5
VAK Russia 5.8.6
VAK Russia 5.8.7
VAK Russia 5.2.2
VAK Russia 1.1.10
VAK Russia 1.2.1
VAK Russia 1.2.2
VAK Russia 1.2.3
VAK Russia 1.5.5
VAK Russia 2.2.11
VAK Russia 2.2.12
VAK Russia 2.3.1
VAK Russia 2.3.4
VAK Russia 2.3.8
UDC 00
UDC 7
UDC 004
UDC 796
UDC 796/799
CSCSTI 28.23
CSCSTI 28.17
CSCSTI 28.01
CSCSTI 77.05
CSCSTI 77.29
CSCSTI 77.31
CSCSTI 80.37
CSCSTI 20.53
CSCSTI 20.01
CSCSTI 50.33
CSCSTI 50.41
CSCSTI 30.51
Russian Classification of Professions by Education 02.04.01
Russian Classification of Professions by Education 02.06.01
Russian Classification of Professions by Education 31.08.39
Russian Classification of Professions by Education 49.02.01
Russian Classification of Professions by Education 49.06.01
Russian Classification of Professions by Education 12.02.06
Russian Library and Bibliographic Classification 75
Russian Library and Bibliographic Classification 6539
Russian Library and Bibliographic Classification 73
Russian Library and Bibliographic Classification 606
Russian Trade and Bibliographic Classification 2352
Russian Trade and Bibliographic Classification 4614
Russian Trade and Bibliographic Classification 4618
Russian Trade and Bibliographic Classification 4612
Russian Trade and Bibliographic Classification 2301
Russian Trade and Bibliographic Classification 3015
Russian Trade and Bibliographic Classification 5106
Russian Trade and Bibliographic Classification 518
Russian Trade and Bibliographic Classification 5182
Russian Trade and Bibliographic Classification 5185
Russian Trade and Bibliographic Classification 762
Russian Trade and Bibliographic Classification 7623
BISAK COM059000 Computer Engineering
BISAK COM012000 Computer Graphics
BISAK COM014000 Computer Science
BISAK COM072000 Computer Simulation
BISAK COM017000 Cybernetics
BISAK COM062000 Data Modeling & Design
BISAK COM018000 Data Processing
BISAK COM021030 Databases / Data Mining
BISAK COM071000 Digital Media / Video & Animation
BISAK COM023000 Educational Software
BISAK COM025000 Expert Systems
BISAK COM074000 Hardware / Mobile Devices
BISAK COM032000 Information Technology
BISAK COM077000 Mathematical & Statistical Software
BISAK BUS021000 Econometrics
BISAK GAM001000 Board Games
BISAK GAM016000 Fantasy Sports
BISAK GAM004050 Gambling / Sports
BISAK EDU039000 Computers & Technology
BISAK EDU036000 Organizations & Institutions
BISAK EDU037000 Research
BISAK EDU027000 Statistics
BISAK MED084000 Sports Medicine
BISAK MED078000 Public Health
BISAK MED076000 Preventive Medicine
BISAK HEA046000 Children's Health
BISAK HEA006000 Diet & Nutrition / Diets
BISAK HEA034000 Diet & Nutrition / Food Content Guides
BISAK HEA002000 Aerobics
BISAK HEA017000 Diet & Nutrition / Nutrition
BISAK HEA007000 Exercise
BISAK HEA010000 Healthy Living
BISAK HEA038000 Work-Related Health
BISAK MAT011000 Game Theory
BISAK MAT029030 Probability & Statistics / Regression Analysis
BISAK MAT025000 Recreations & Games
BISAK SPO003000 Baseball / General
BISAK SPO068000 Business Aspects
BISAK SPO077000 Children’s & Youth Sports
BISAK SPO061020 Coaching / Football
BISAK SPO061030 Coaching / Soccer
BISAK SPO011000 Cycling
BISAK SPO063000 Equipment & Supplies
BISAK SPO073000 Field Hockey
BISAK SPO015000 Football
BISAK SPO016000 Golf
BISAK SPO075000 Health & Safety
BISAK SPO024000 Juggling
BISAK SPO040000 Soccer
BISAK SPO066000 Sociology of Sports
BISAK SPO047000 Training
BISAK SPO051000 Water Sports
BISAK PSY012000 Education & Training
BISAK PSY042000 Assessment, Testing & Measurement
VAK Russia 5.8.5
VAK Russia 5.8.6
VAK Russia 5.8.7
VAK Russia 5.2.2
VAK Russia 1.1.10
VAK Russia 1.2.1
VAK Russia 1.2.2
VAK Russia 1.2.3
VAK Russia 1.5.5
VAK Russia 2.2.11
VAK Russia 2.2.12
VAK Russia 2.3.1
VAK Russia 2.3.4
VAK Russia 2.3.8
UDC 00
UDC 7
UDC 004
UDC 796
UDC 796/799
CSCSTI 28.23
CSCSTI 28.17
CSCSTI 28.01
CSCSTI 77.05
CSCSTI 77.29
CSCSTI 77.31
CSCSTI 80.37
CSCSTI 20.53
CSCSTI 20.01
CSCSTI 50.33
CSCSTI 50.41
CSCSTI 30.51
Russian Classification of Professions by Education 02.04.01
Russian Classification of Professions by Education 02.06.01
Russian Classification of Professions by Education 31.08.39
Russian Classification of Professions by Education 49.02.01
Russian Classification of Professions by Education 49.06.01
Russian Classification of Professions by Education 12.02.06
Russian Library and Bibliographic Classification 75
Russian Library and Bibliographic Classification 6539
Russian Library and Bibliographic Classification 73
Russian Library and Bibliographic Classification 606
Russian Trade and Bibliographic Classification 2352
Russian Trade and Bibliographic Classification 4614
Russian Trade and Bibliographic Classification 4618
Russian Trade and Bibliographic Classification 4612
Russian Trade and Bibliographic Classification 2301
Russian Trade and Bibliographic Classification 3015
Russian Trade and Bibliographic Classification 5106
Russian Trade and Bibliographic Classification 518
Russian Trade and Bibliographic Classification 5182
Russian Trade and Bibliographic Classification 5185
Russian Trade and Bibliographic Classification 762
Russian Trade and Bibliographic Classification 7623
BISAK COM059000 Computer Engineering
BISAK COM012000 Computer Graphics
BISAK COM014000 Computer Science
BISAK COM072000 Computer Simulation
BISAK COM017000 Cybernetics
BISAK COM062000 Data Modeling & Design
BISAK COM018000 Data Processing
BISAK COM021030 Databases / Data Mining
BISAK COM071000 Digital Media / Video & Animation
BISAK COM023000 Educational Software
BISAK COM025000 Expert Systems
BISAK COM074000 Hardware / Mobile Devices
BISAK COM032000 Information Technology
BISAK COM077000 Mathematical & Statistical Software
BISAK BUS021000 Econometrics
BISAK GAM001000 Board Games
BISAK GAM016000 Fantasy Sports
BISAK GAM004050 Gambling / Sports
BISAK EDU039000 Computers & Technology
BISAK EDU036000 Organizations & Institutions
BISAK EDU037000 Research
BISAK EDU027000 Statistics
BISAK MED084000 Sports Medicine
BISAK MED078000 Public Health
BISAK MED076000 Preventive Medicine
BISAK HEA046000 Children's Health
BISAK HEA006000 Diet & Nutrition / Diets
BISAK HEA034000 Diet & Nutrition / Food Content Guides
BISAK HEA002000 Aerobics
BISAK HEA017000 Diet & Nutrition / Nutrition
BISAK HEA007000 Exercise
BISAK HEA010000 Healthy Living
BISAK HEA038000 Work-Related Health
BISAK MAT011000 Game Theory
BISAK MAT029030 Probability & Statistics / Regression Analysis
BISAK MAT025000 Recreations & Games
BISAK SPO003000 Baseball / General
BISAK SPO068000 Business Aspects
BISAK SPO077000 Children’s & Youth Sports
BISAK SPO061020 Coaching / Football
BISAK SPO061030 Coaching / Soccer
BISAK SPO011000 Cycling
BISAK SPO063000 Equipment & Supplies
BISAK SPO073000 Field Hockey
BISAK SPO015000 Football
BISAK SPO016000 Golf
BISAK SPO075000 Health & Safety
BISAK SPO024000 Juggling
BISAK SPO040000 Soccer
BISAK SPO066000 Sociology of Sports
BISAK SPO047000 Training
BISAK SPO051000 Water Sports
BISAK PSY012000 Education & Training
BISAK PSY042000 Assessment, Testing & Measurement
Language:
Russian, English
Keywords:
go game, baduk, weiqi, KataGo, neural networks
Abstract (English):
The article describes testing a weakness of the go-playing AI KataGo (9d) detected by K. Pelrine et al. Building groups following the developed 4-level algorithm reveals the incapability of AI to understand intentional sacrifice of larger groups and to prioritize when discovering several similar sacrifices on the board. The value of the developed strategy lies in human victory over a potentially unbeatable program even regarding the fact that human is playing on the level of 1q (2000 Elo).
The article describes testing a weakness of the go-playing AI KataGo (9d) detected by K. Pelrine et al. Building groups following the developed 4-level algorithm reveals the incapability of AI to understand intentional sacrifice of larger groups and to prioritize when discovering several similar sacrifices on the board. The value of the developed strategy lies in human victory over a potentially unbeatable program even regarding the fact that human is playing on the level of 1q (2000 Elo).
Keywords:
go game, baduk, weiqi, KataGo, neural networks
go game, baduk, weiqi, KataGo, neural networks
1. AlphaGo by Google DeepMind. URL: https://www.deepmind.com/research/highlighted-research/alphago (accessed 20.09.2023).
2. KataGo on GitHub. URL: https://github.com/lightvector/KataGo/releases?q=v1.12.4&expanded=true (accessed 20.09.2023).
3. Leela official website. URL: https://www.sjeng.org/leela.html (accessed 20.09.2023).
4. Lauder E. Tencent's Made a Go-Playing AI to Rival Google's AlphaGo. URL: https://aibusiness.com/companies/tencent-s-made-a-go-playing-ai-to-rival-google-s-alphago (accessed 20.09.2023).
5. Wang T.T., Gleave A., Tseng T., Pelrine K., Belrose N. et al. Adversarial policies beat superhuman Go AIs // arXiv:2211.00241 [cs.LG]. URL: https://goattack.far.ai/adversarial-policy-katago (accessed 20.09.2023). DOI:https://doi.org/10.48550/arXiv.2211.00241
6. Financial Times. Man beats machine at Go in human victory over AI. URL: https://www.ft.com/content/175e5314-a7f7-4741-a786-273219f433a1 (accessed 27.11.2023).
