Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this community
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.
