News for hackers. Stuff that matters.
Re:To Build Truly Intelligent Machines, Teach Them Cause and... by cweill on Tuesday January 03, 2023 @11:41PM (#34242104)
I also have this question. Is the RL MDP actually encoding cause and effect? Or just learning (bidirectional) correlations between states and actions?

I wonder if Pearl thinks that RL replicates his do-calculus under the hood, or if that's an innovation we're missing.

There are no comments on this comment yet.