I am trying to solve a MDP problem with almost 50 states and 60 actions with Q-Learning or SARSA. However, the performance of both algorithms is terrible and cannot find the optimal policy found by backward induction. Does it mean that these algorithms do not converge to the optimal policies or there are some other problems? I run the algorithms for 100k, 500k and 1m episodes but I could not find the optimal policy.

  • 1
    $\begingroup$ we would need more information about the MDP before this question is answerable. $\endgroup$ – David Ireland Jun 30 at 11:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.