Chess, once famously referred to as the drosophila of artificial
intelligence (AI) research, has been a significant domain for developing
intelligent AI agents capable of achieving super-human performance in domains
previously dominated by humans. However, the emphasis on unceasingly improved
playing strength has come at the cost of neglecting other fundamental aspects of
intelligent agents, such as being capable of explaining the rationality behind
their decisions in human-understandable terms. The need for such capabilities
may be even more profound now than before, partly because such agents may be
capable of learning novel concepts of interest to us humans, for example, as
recently demonstrated in the game of chess. In this paper, we survey the state
of explainable AI in chess-playing agents, arguing that chess may indeed hold a
promise as an admissible domain for explainable AI.
Alain, G.
& Bengio,
Y. (2018).
Understanding intermediate layers using linear classifier
probes.
2.
Baier, H.
& Kaisers,
M. (2020).
Explainable search. In IJCAI-PRICAI
Workshop on Explainable Artificial Intelligence.
3.
Baier, H.
& Kaisers,
M. (2021).
Towards explainable MCTS. In AAAI
Workshop on Explainable Agency in AI.
4.
Bratko, I.
(2018). AlphaZero – What’s Missing? Informatica
(Slovenia), 42.
5.
Chakraborti,
T., Kulkarni,
A., Sreedharan,
S., Smith,
D.E. & Kambhampati,
S. (2018).
Explicability? Legibility? Predictability? Transparency? Privacy? Security? The
Emerging Landscape of Interpretable Agent Behavior. CoRR.
arXiv:1811.09722.
6.
Chakraborti,
T., Sreedharan,
S. & Kambhampati,
S. (2020).
The Emerging Landscape of Explainable AI Planning and Decision
Making.
7.
DecodeChess. Chess Analysis, Powered by AI.
https://decodechess.com/.
8.
Fischer, B.
(2012). My 60 Memorable Games: chess tactics, chess
strategies with Bobby Fischer. Batsford Chess. Pavilion
Books.
9.
Fritz, J.
& Fürnkranz,
J. (2021).
Some chess-specific improvements for perturbation-based
saliency maps. In 2021 IEEE Conference on Games
(CoG) (pp. 01–08). doi:10.1109/CoG52621.2021.9619015.
10.
Ghorbani,
A., Wexler,
J., Zou,
J.Y. & Kim,
B. (2019).
Towards automatic concept-based explanations.
In H.Wallach,
H.Larochelle,
A.Beygelzimer,
F.d’Alché-Buc,
E.Fox and
R.Garnett
(Eds.), Advances in Neural Information Processing Systems
(Vol. 32). Curran Associates,
Inc.https://proceedings.neurips.cc/paper_files/paper/2019/file/77d2afcb31f6493e350fca61764efb9a-Paper.pdf.
11.
Guid, M.,
Mozina,
M., Bohak,
C., Sadikov,
A. & Bratko,
I. (2013).
Building an intelligent tutoring system for chess
endgames. In O.Foley,
M.T.Restivo,
J.O.Uhomoibhi
and M.Helfert
(Eds.), CSEDU 2013 – Proceedings of the 5th International Conference on
Computer Supported Education, Aachen, Germany,
6–8 May, 2013 (pp.
263–266).
SciTePress.
12.
Kadir, T.
& Brady,
M. (2001).
Saliency, scale and image description.
International Journal of Computer Vision,
45(2), 83–105.
doi:10.1023/A:1012460413855.
13.
Kim, B.,
Wattenberg,
M., Gilmer,
J., Cai,
C., Wexler,
J., Viegas,
F. & Sayres,
R. (2018).
Interpretability beyond feature attribution: Quantitative
testing with concept activation vectors (TCAV). In
J.Dy and
A.Krause
(Eds.), Proceedings of the 35th International Conference on Machine
Learning. Proceedings of Machine Learning Research
(Vol. 80, pp. 2668–2677).
PMLR.
https://proceedings.mlr.press/v80/kim18d.html.
14.
Langley, P.
(2019). Varieties of explainable
agency. In ICAPS 2019 Workshop on Explainable AI
Planning (XAIP).
15.
Langley,
P., Meadows,
B., Sridharan,
M. & Choi,
D. (2017).
Explainable agency for intelligent autonomous
systems. In S.P.Singh
and S.Markovitch
(Eds.), Proceedings of the Thirty-First AAAI Conference on Artificial
Intelligence, San Francisco, California, USA,
February 4–9, 2017 (pp.
4762–4764). AAAI
Press.
16.
Lee, A.,
Wu,
D., Dinan,
E. & Lewis,
M. (2022).
Improving Chess Commentaries by Combining Language Models with
Symbolic Reasoning Engines.
17.
Lovering,
C., Forde,
J., Konidaris,
G., Pavlick,
E. & Littman,
M. (2022).
Evaluation beyond task performance: Analyzing concepts in
AlphaZero in Hex. In S.Koyejo,
S.Mohamed,
A.Agarwal,
D.Belgrave,
K.Cho and
A.Oh
(Eds.), Advances in Neural Information Processing Systems
(Vol. 35, pp. 25992–26006).
Curran Associates, Inc,
https://proceedings.neurips.cc/paper_files/paper/2022/file/a705747417d32ebf1916169e1a442274-Paper-Conference.pdf.
18.
Lundberg,
S.M. & Lee,
S.-I. (2017).
A unified approach to interpreting model
predictions. In I.Guyon,
U.V.Luxburg,
S.Bengio,
H.Wallach,
R.Fergus,
S.Vishwanathan
and R.Garnett
(Eds.), Advances in Neural Information Processing Systems
(Vol. 30). Curran Associates,
Inc.https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf.
19.
McGrath,
T., Kapishnikov,
A., Tomašev,
N., Pearce,
A., Wattenberg,
M., Hassabis,
D., Kim,
B., Paquet,
U. & Kramnik,
V. (2022).
Acquisition of chess knowledge in AlphaZero.
In Proceedings of the National Academy of Sciences
(Vol. 119).
20.
Michie, D.
(1988). Machine learning in the next five
years. In Proc. Third European Working Session on
Learning (EWSL) (pp.
107–122).
21.
Pálsson, A.
& Björnsson,
Y. (2022).
Evaluating interpretability methods for DNNs in game-playing
agents. In C.Browne,
A.Kishimoto
and J.Schaeffer
(Eds.), Advances in Computer Games (pp.
71–81). Cham:
Springer. doi:10.1007/978-3-031-11488-5_7.
22.
Pálsson, A.
& Björnsson,
Y. (2023).
Unveiling Concepts Learned by a World-Class Chess-Playing Agent. In
International Joint Conference on Artificial Intelligence
(IJCAI23).
23.
Pascutto,
G.-C., Linscott,
G., Lyaskuk,
A. & Huizinga,
F. (2023). Leela
Chess Zero. http://lczero.org.
24.
Ribeiro,
M., Singh, S.
& Guestrin,
C. (2016).
“Why should I trust you?”: Explaining the predictions of any
classifier. In Proceedings of the 2016 Conference of
the North American Chapter of the Association for Computational Linguistics:
Demonstrations (pp. 97–101).
San Diego, California:
Association for Computational Linguistics.
https://aclanthology.org/N16-3020.
doi:10.18653/v1/N16-3020.
25.
Romstad,
T., Costalba,
M., Kiiski,
J., Linscott,
G., Nicolet,
S., Geschwentner,
S. & VandeVondele,
J. (2023).
Stockfish. https://stockfishchess.org.
26.
Sadikov,
A., Mozina, M.,
Guid,
M., Krivec,
J. & Bratko,
I. (2006).
Automated chess tutor. In H.J.van den
Herik, P.Ciancarini
and H.H.L.M.Donkers
(Eds.), Computers and Games. Lecture Notes in Computer
Science (Vol. 4630, pp.
13–25).
Springer. doi:10.1007/978-3-540-75538-8_2.
27.
Schut, L.,
Tomasev,
N., McGrath,
T., Hassabis,
D., Paquet,
U. & Kim,
B. (2023). Bridging
the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero.
CoRR. arXiv:2310.16410. doi:10.48550/ARXIV.2310.16410.
28.
Schwalbe,
G. & Finzel,
B. (2023).
A comprehensive taxonomy for explainable artificial
intelligence: A systematic survey of surveys on methods and
concepts. Data Mining and Knowledge
Discovery. doi:10.1007/s10618-022-00867-8.
29.
Silver, D.,
Hubert,
T., Schrittwieser,
J., Antonoglou,
I., Lai,
M., Guez,
A., Lanctot,
M., Sifre,
L., Kumaran,
D., Graepel,
T., et
al. (2018). A general reinforcement
learning algorithm that masters chess, shogi, and go through
self-play. Science,
362(6419),
1140–1144. doi:10.1126/science.aar6404.
30.
Simonyan,
K., Vedaldi,
A. & Zisserman,
A. (2014).
Deep inside convolutional networks: Visualising image
classification models and saliency maps. In Workshop
at International Conference on Learning
Representations.
31.
Zang, H.,
Yu,
Z. & Wan,
X. (2019).
Automated chess commentator powered by neural chess
engine. In A.Korhonen,
D.R.Traum
and L.Màrquez
(Eds.), Proceedings of the 57th Conference of the Association for
Computational Linguistics, ACL 2019, Florence,
Italy, July 28–August 2, 2019,
Volume 1: Long Papers (pp.
5952–5961). Association for
Computational Linguistics. doi:10.18653/v1/p19-1597.
