It looks like someone has taken the AlphaGo Zero approach to program synthesis sans reversible programming.
https://www.youtube.com/watch?v=qtu0aSTDE2I On Wed, Mar 24, 2021 at 11:50 AM James Bowery <[email protected]> wrote: > > > On Wed, Mar 24, 2021 at 9:09 AM Ben Goertzel <[email protected]> wrote: > >> ... >> discussed the issue of identifying which theorems are "interesting." >> >> One goal of this is: If you can tractably make a looooong list of >> interesting conjectures... >> > > That was what I had in mind when I suggested that the wxMaxima software > include an option for the user to share their derivations with a central > repository. > > But in the particular case of Solomonoff Induction, "interesting" has a > clear definition of "shorter". So it seems an AlphaGo Zero approach may > work. > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf8bb7754cbb517a4-M12e1dc3655b8566cb3808b3d Delivery options: https://agi.topicbox.com/groups/agi/subscription
