Recursive Stochastic Games with Positive Rewards

  title={Recursive Stochastic Games with Positive Rewards},
  author={Kousha Etessami and Dominik Wojtczak and Mihalis Yannakakis},
We study the complexity of a class of Markov decision processes and, more generally, stochastic games, called 1-exit Recursive Markov Decision Processes (1-RMDPs) and Simple Stochastic Games (1-RSSGs) with strictly positive rewards. These are a class of finitely presented countable-state zero-sum stochastic games, with total expected reward objective. They subsume standard finite-state MDPs and Condon’s simple stochastic games and correspond to optimization and game versions of several classic… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS
18 Citations
30 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 18 extracted citations


Publications referenced by this paper.

Similar Papers

Loading similar papers…