Login / Signup
On Optimal Policies in Structured Markovian Decision Models.
Dieter Kalin
Published in:
J. Inf. Process. Cybern. (1981)
Keyphrases
</>
optimal policy
markov decision processes
decision problems
state space
stochastic inventory control
reinforcement learning
cost function
dynamic programming
finite horizon
average reward reinforcement learning
probabilistic model
long run
policy iteration
control policies
markovian decision