Step into a world of fun learning at RBA Royale Business Academy! Our friendly classes make education exciting and easy. Each lesson is a adventure that boosts creativity, builds confidence, and sparks curiosity 😊. Join us to learn, grow, and shine bright with us! 😄 #LearnFun #BrightFuture #TeamRBA

Very cool! Reminds me a lot of how Tom7's Playfun/Learnfun plays SMB: youtu.be/xOCurBYI_gY?...

there was a pair of algorithms called learnfun and playfun designed to use data from a few minutes of training inputs plus comparing the values of current vs future states to win at any NES game

look up learnfun playfun

Look up learnfun/playfun to get a feel for what kind of problems this goes into.

To be clear, Learnfun was a system based on using ONLY the domain knowledge of "number goes up", showing how it was possible to discover which hidden variables mattered, sorta. So if really you wanted to go down a domain-knowledge-free path, there are some possibilities. Doubt they'd go 100% though.

Yeah. It's definitely possible to imagine feeding the RAM into a model. Compare, for example, tom7's semi-jokey Learnfun/Playfun effort in 2013 doing ML on an NES's 2048 bytes of RAM. (1/2)

www.youtube.com/watch?v=xOCu...