Bright key facts / Emerging
Ataraxos AI beat a Stratego champion by planning around hidden information
Ataraxos won 15 of 20 games against a Stratego champion. Its hidden-information planning and estimated training compute below $8,000, explained.
- AI’s role
- Ataraxos combines self-play reinforcement learning with decision-time planning using plausible models of hidden piece identities.
- Documented result
- The headline test was a 20-game series against Pim Niemeijer, a four-time world champion. Ataraxos won 15 games, lost one and drew four.
- Important limitation
- That is a compute estimate, rather than an accounting of salaries, development and every experiment behind the project.