self-play
Everything on Ground Truth tagged “self-play” — 3 items.
Imperfect-information games: how AI plays when it cannot see the whole board Lesson
In imperfect-information games like poker and Stratego, players hold private information, so an AI must reason about what its opponent might know and mix its own actions unpredictably; belief states and regret-based methods are how modern systems do it.
Ataraxos beat Stratego's most decorated champion 15-1 after a training run that cost under $8,000 News
Ataraxos, an AI built by researchers at Carnegie Mellon, NYU, Stanford and MIT, beat four-time Stratego world champion Pim Niemeijer 15 games to 1 with four draws, after training the authors estimate cost under $8,000.
Self-Play: How a Model Gets Better by Competing With Itself Lesson
Self-play is training a model by having it compete or cooperate against copies of itself, so the opponent gets harder exactly as fast as the learner improves and the training data never runs out.