← All projects

Counterfactual Regret Exploration (CFR-Min)

Nov 2024 – Present
JupyterNumPyReinforcement Learning

Highlights

  • Exploring CFR-Min for Nash equilibria in imperfect-information games.
  • Worked examples: Colonel Blotto, Kuhn Poker.
  • Toward general application for sequential games (Risk, Poker).