tag:blogger.com,1999:blog-6923947282926324208.post6448190737761761311..comments2024-03-08T09:15:52.903+01:00Comments on Entropic and Fractal Intelligence: The Gordian Knot of AGISergio Hernandezhttp://www.blogger.com/profile/18108694861191833007noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-6923947282926324208.post-41572272602230689442019-06-17T13:04:42.454+02:002019-06-17T13:04:42.454+02:00Yes. Basically, any algorithm doing planning based...Yes. Basically, any algorithm doing planning based on a Monte Carlo Tree Search can replace this MCTS with a Fractal Monte Carlo equivalent.<br /><br />Basically, you get a much better performance in the planning part, allowing you to scan much deeper into the future (as doubling depth just cost double time in FMC), and a more reliable decision (as it is based on choosing the highest entropy one).Sergio Hernandezhttps://www.blogger.com/profile/18108694861191833007noreply@blogger.comtag:blogger.com,1999:blog-6923947282926324208.post-67837392843626516972019-06-16T18:18:08.999+02:002019-06-16T18:18:08.999+02:00Might "A Monte Carlo AIXI Approximation"...Might "A Monte Carlo AIXI Approximation" be improved by FMC? See: https://arxiv.org/abs/0909.0801Jim Boweryhttps://www.blogger.com/profile/12686155123469135528noreply@blogger.com