Summary

Ataraxos won 15 games, lost one and drew four against Pim Niemeijer, described by the researchers as the most decorated Stratego player historically. The system trained on roughly 160 million games, compared with about 5.5 billion for DeepNash, and also performed strongly on Hanabi and dou dizhu.

Why it matters

The result suggests that better search, self-play and hidden-information modelling can deliver strong planning performance without frontier-scale compute.

Sources