Student of Games: A unified learning algorithm for both perfect and imperfect information games

M Schmid, M Moravčík, N Burch, R Kadlec… - Science …, 2023 - science.org
Games have a long history as benchmarks for progress in artificial intelligence. Approaches
using search and learning produced strong performance across many perfect information …

Solving zero-sum one-sided partially observable stochastic games

K Horák, B Bošanský, V Kovařík, C Kiekintveld - Artificial Intelligence, 2023 - Elsevier
Many real-world situations are dynamic, with long-term interactions between multiple agents
with uncertainty and limited observations. The agents must reason about which actions to …

Search in imperfect information games

M Schmid - arXiv preprint arXiv:2111.05884, 2021 - arxiv.org
From the very dawn of the field, search with value functions was a fundamental concept of
computer games research. Turing's chess algorithm from 1950 was able to think two moves …

Value functions for depth-limited solving in zero-sum imperfect-information games

V Kovařík, D Seitz, V Lisý, J Rudolf, S Sun, K Ha - Artificial Intelligence, 2023 - Elsevier
We provide a formal definition of depth-limited games together with an accessible and
rigorous explanation of the underlying concepts, both of which were previously missing in …

[PDF][PDF] Value functions for depth-limited solving in imperfect-information games

V Kovarık, D Seitz, V Lisy, J Rudolf… - … Learning in Games …, 2021 - rlg.mlanctot.info
We provide a formal definition of depth-limited games together with an accessible and
rigorous explanation of the underlying concepts, both of which were previously missing in …

Sound algorithms in imperfect information games

M Šustr, M Schmid, M Moravčík, N Burch… - arXiv preprint arXiv …, 2020 - arxiv.org
Search has played a fundamental role in computer game research since the very beginning.
And while online search has been commonly used in perfect information games such as …