Glossary · RSI and self-improvement
Self-play
Training in which the model generates its own tasks, opponents, or curricula, including proposer–solver loops and zero-data regimes that start from a base model with no external task set.
Glossary · RSI and self-improvement
Training in which the model generates its own tasks, opponents, or curricula, including proposer–solver loops and zero-data regimes that start from a base model with no external task set.