causal

Value function amortizes deep search into a glance

A value function lets a network look at a board and instantly predict win probability—amortizing a huge number of possible game playouts into a single forward pass—just as humans glance at a board and 'know' they will lose without playing it out; this is the key to truncating search depth in Go.

causalpending

Speaker

Eric Jang

Evidence Quote

“You can train a value function to look at a board and quickly resolve the game without playing out all of these trees to a very deep search depth.”

Source

Dwarkesh Patel Podcast - Eric Jang – Building AlphaGo from scratch— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:37:56 AM

Your notes

Loading notes...