van der Wal, J. Stochastic dynamic programming. Successive approximations and nearly optimal strategies for Markov decision processes and Markov games. (English) Zbl 0462.90055 Mathematical Centre Tracts, 139. Amsterdam: Mathematisch Centrum. III, 251 p. Dfl. 32.55 (1981). Page: −5 −4 −3 −2 −1 ±0 +1 +2 +3 +4 +5 Show Scanned Page Cited in 17 Documents MSC: 91A40 Other game-theoretic models 91A05 2-person games 90C39 Dynamic programming 90C15 Stochastic programming Keywords:stochastic dynamic programming; Markov decision processes; average reward criterion; total reward criterion; two person zero-sum Markov games; successive approximations; value algorithms; nearly optimal strategies; go-ahead strategies; Liapunov functions; conservingness; strong convergence; policy space algorithms; epsilon-optimal stationary Markov strategies PDF BibTeX XML