Chess endgame AI

Theory, graphs, and math

Chess positions are basically one huge directed graph: each position is a state, and each legal move is an edge to another state. Endgames make that graph small enough to actually study, which makes them a great place to explore search, value approximation, and machine learning. This also connects to my interests in theoretical computer science and my mathematics minor, especially linear algebra. Neural networks are built from weights, activations, and compositions of linear maps, so ideas like rank, bases, and eigenstructure help me reason about what a model can actually represent.

Notebooks & code

View our CNN training algorithm, and gameplay loops here!

• chess_training.ipynb Training
• chess_gameplay_loop.ipynb Gameplay loop
• chess_gameplay2.ipynb Gameplay variant
• chess_with_actual_dtm.ipynb Distance-to-mate