Jun 13, 2026·10 min read
MCTS as Regularized Policy Optimization
Deriving pUCT from first principles
Jun 8, 2026·11 min read
Deconstructing AlphaGo: Exploring Monte Carlo Tree Search
What do you do when there are too many possibilities?
Jul 14, 2025·7 min read
dpbusd, explained
Demystifying multi-layer inference.