2
$\begingroup$

The Q-learning does not guarantee convergence for continuous state space problems (Why doesn't Q-learning converge when using function approximation?). In that case, is there an algorithm which can guarantee convergence?

I am looking at model-based RL specifically iLQR but all the solutions I find are for the continuous action space problem.

$\endgroup$

0

You must log in to answer this question.

Browse other questions tagged .