Discrete Dynamic Programming with Unbounded Rewards

DOI10.1214/aoms/1177692643zbMath0262.90064OpenAlexW2120527407MaRDI QIDQ5678679

J. Michael Harrison

Publication date: 1972

Published in: The Annals of Mathematical Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoms/1177692643

Mathematics Subject Classification ID

Decision theory (91B06) Markov processes: estimation; hidden Markov models (62M05) Markov and semi-Markov decision processes (90C40) Hamilton-Jacobi theories (49L99) Compound decision problems in statistical decision theory (62C25)

Related Items

Finite-state approximations for denumerable state discounted Markov decision processes ⋮ On theory and algorithms for Markov decision problems with the total reward criterion ⋮ Denumerable semi-Markov decision chains with small interest rates ⋮ Discounted and average Markov decision processes with unbounded rewards: New conditions ⋮ Approximate dynamic programming via direct search in the space of value function approximations ⋮ The effect on optimal consumption on increased uncertainty in labor income in the multiperiod case ⋮ On the properties of \(\epsilon\) (\(\geq 0)\) optimal policies in discounted unbounded return model ⋮ Markov programming by successive approximations with respect to weighted supremum norms ⋮ Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards