The Second NeurIPS Tournament of Reconnaissance Blind Chess

Gino Perrotta, Ryan W. Gardner, Corey Lowman, Mohammad Taufeeque, Nitish Tongia, Shivaram Kalyanakrishnan, Gregory Clark, Kevin Wang, Eitan Rothberg, Brady P. Garrison, Prithviraj Dasgupta, Callum Canavan, Lucas McCabe
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:53-65, 2022.

Abstract

Reconnaissance Blind Chess is an imperfect-information variant of chess with significant private information that challenges state-of-the-art algorithms. The Johns Hopkins University Applied Physics Laboratory and several organizing partners held the second NeurIPS machine Reconnaissance Blind Chess competition in 2021. 18 bots competed in 9,180 games, revealing a dominant champion with 91% wins. The top four bots in the tournament matched or exceeded the performance of the inaugural tournament’s winner. However, none of the algorithms converge to an optimal, unexploitable strategy or appear to have addressed the core research challenges associated with Reconnaissance Blind Chess.

Cite this Paper

BibTeX
@InProceedings{pmlr-v176-perrotta22a, title = {The Second NeurIPS Tournament of Reconnaissance Blind Chess}, author = {Perrotta, Gino and Gardner, Ryan W. and Lowman, Corey and Taufeeque, Mohammad and Tongia, Nitish and Kalyanakrishnan, Shivaram and Clark, Gregory and Wang, Kevin and Rothberg, Eitan and Garrison, Brady P. and Dasgupta, Prithviraj and Canavan, Callum and McCabe, Lucas}, booktitle = {Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track}, pages = {53--65}, year = {2022}, editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara}, volume = {176}, series = {Proceedings of Machine Learning Research}, month = {06--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v176/perrotta22a/perrotta22a.pdf}, url = {https://proceedings.mlr.press/v176/perrotta22a.html}, abstract = {Reconnaissance Blind Chess is an imperfect-information variant of chess with significant private information that challenges state-of-the-art algorithms. The Johns Hopkins University Applied Physics Laboratory and several organizing partners held the second NeurIPS machine Reconnaissance Blind Chess competition in 2021. 18 bots competed in 9,180 games, revealing a dominant champion with 91% wins. The top four bots in the tournament matched or exceeded the performance of the inaugural tournament’s winner. However, none of the algorithms converge to an optimal, unexploitable strategy or appear to have addressed the core research challenges associated with Reconnaissance Blind Chess.} }
Endnote
%0 Conference Paper %T The Second NeurIPS Tournament of Reconnaissance Blind Chess %A Gino Perrotta %A Ryan W. Gardner %A Corey Lowman %A Mohammad Taufeeque %A Nitish Tongia %A Shivaram Kalyanakrishnan %A Gregory Clark %A Kevin Wang %A Eitan Rothberg %A Brady P. Garrison %A Prithviraj Dasgupta %A Callum Canavan %A Lucas McCabe %B Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track %C Proceedings of Machine Learning Research %D 2022 %E Douwe Kiela %E Marco Ciccone %E Barbara Caputo %F pmlr-v176-perrotta22a %I PMLR %P 53--65 %U https://proceedings.mlr.press/v176/perrotta22a.html %V 176 %X Reconnaissance Blind Chess is an imperfect-information variant of chess with significant private information that challenges state-of-the-art algorithms. The Johns Hopkins University Applied Physics Laboratory and several organizing partners held the second NeurIPS machine Reconnaissance Blind Chess competition in 2021. 18 bots competed in 9,180 games, revealing a dominant champion with 91% wins. The top four bots in the tournament matched or exceeded the performance of the inaugural tournament’s winner. However, none of the algorithms converge to an optimal, unexploitable strategy or appear to have addressed the core research challenges associated with Reconnaissance Blind Chess.
APA
Perrotta, G., Gardner, R.W., Lowman, C., Taufeeque, M., Tongia, N., Kalyanakrishnan, S., Clark, G., Wang, K., Rothberg, E., Garrison, B.P., Dasgupta, P., Canavan, C. & McCabe, L.. (2022). The Second NeurIPS Tournament of Reconnaissance Blind Chess. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, in Proceedings of Machine Learning Research 176:53-65 Available from https://proceedings.mlr.press/v176/perrotta22a.html.

Related Material