Machine Learning AI Research2 min reading time

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

Ars TechnicaPublished 24 days ago

Researchers from Carnegie Mellon, MIT, NYU, and Stanford developed Ataraxos, an AI that decisively defeated top Stratego player Pim Niemeijer using modest computing resources. Stratego's complexity lies in its vast hidden information and long gameplay, which challenged prior AIs. Ataraxos overcame these hurdles, winning 15-1 with four draws against Niemeijer.

#ataraxos #carnegie-mellon #game-ai #imperfect-information-games #mit #new-york-university #stanford-university

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

More in Machine Learning

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

AI21 Labs Releases LIFT-Bench to Curb Reward Hacking in RL Training

OpenAI Resumes Training AI, But Without Internet Access