I'm aware that convergence proofs for Monte Carlo tree search exist in the case of deterministic zero sum games and Markov decision processes.

I have come across research which applies MCTS to zero-sum stochastic games, however I was unable to find proof that such an approach is guaranteed to converge to the optimal solution.

If anyone is able to provide references or an explanation explaining why or why not MCTS is guaranteed to converge to the optimal solution in this setting I would appreciate it a lot.


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.