Minimizing spectral risk measures applied to Markov decision processes.

Nicole Bäuerle Alexander Glauner

Published in: Math. Methods Oper. Res. (2021)

Keyphrases

markov decision processes
risk measures
optimal policy
finite state
reinforcement learning
state space
transition matrices
dynamic programming
decision making
average reward
decision theoretic planning
multi objective
decision problems
average cost
policy iteration