A note on the structure of value spaces in vector-valued Markov decision processes.

Kazuyoshi Wakuta

Published in: Math. Methods Oper. Res. (1999)

Keyphrases

markov decision processes
vector valued
state space
optimal policy
policy iteration
finite state
reinforcement learning
transition matrices
dynamic programming
average reward
decision theoretic planning
reproducing kernel hilbert space
vector quantization
markov decision process