Re:Why traditional reinforcement learning will probably not ...
by eli_gottlieb on Wednesday October 21, 2020 @10:41PM
(#24854402)
>Reinforcement learning is Turing complete [1], so if AI is possible at all, then it can be realised through RL.
Brainfuck is also Turing complete, so logically if we just do, for instance, Markov chain Monte Carlo for Bayesian program learning in Brainfuck, we can realize AGI that way.
"Everything is possible, but nothing is easy." The Turing tarpit.
Brainfuck is also Turing complete, so logically if we just do, for instance, Markov chain Monte Carlo for Bayesian program learning in Brainfuck, we can realize AGI that way.
"Everything is possible, but nothing is easy." The Turing tarpit.