> but so could a Markov chain if it was built to optimize a different objective (though it wouldn't be a Markov chain anymore I don't think).

i wanted to think about this, and i thought maybe you could have a purely markov model if it were a self constructing self similar model

a markov fractal

at each event the chain reconstructs itself from its new perspective in the fractal

but even done elegantly i think it would be more undue overhead to constantly reconstruct the model than just feeding a self similar model constantly reconstructed inputs, which i see a more clear affinity to neural networks or something wholly different than either