Topics · Concept

Self-play

A program improving by playing itself: generating its own training data, learning from the outcomes, and testing each generation against the last.

Within
Reinforcement learning, Game AI
Pages
1
On the map 1 page and the topics around it
Tap a dot to select it, tap again to open it.

Open in the full map →

  1. 2026

  2. articleThe Engine Plays Itself

    Self-play as reinforcement learning: the engine makes its own training data, a network learns to predict the outcome, and one unfitted constant cost 176 Elo.

    10 min readGame AISelf-playReinforcement learningTraining data

    Open the full search →