Optimal non-linear reinforcement schemes for stochastic automata.

S. Lakshmivarahan M. A. L. Thathachar

Published in: Inf. Sci. (1972)

Keyphrases

approximation schemes
probabilistic automata
monte carlo
reinforcement learning
optimal solution
dynamic programming
state dependent
case study
optimal control
finite state
globally optimal
optimal strategy
stochastic dynamic programming