With most information hidden, the game Stratego had stumped AI until now

[PaulHoule]

Scalable decision-making for games of imperfect information - Nature
Superhuman AI for Stratego Using Self-Play Reinforcement Learning and Test-Time Search

---

Comments URL: With most information hidden, the game Stratego had stumped AI until now | Hacker News

Points: 137

# Comments: 58

Continue reading...