factual

Random play bootstraps value functions on small boards

On small boards (4x4 up to 9x9), purely random play over ~50,000 games generates reasonable-looking end states that can be scored easily, yielding a good value function; combined with architectures that transfer between 9x9 and 19x19, this dramatically cuts the warm-start time for tabula rasa learning.

factualpending

Speaker

Eric Jang

Evidence Quote

“there's pretty good transfer learning from the value head evaluated at 9x9 to 19x19.”

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...