Optimistic Value Iteration.

Arnd Hartmanns Benjamin Lucien Kaminski

Published in: CAV (2) (2020)

Keyphrases

markov decision processes
heuristic search
state space
markov decision chains
optimal policy

policy iteration
partially observable markov
dynamic programming
markov decision process
belief space

infinite horizon
partially observable markov decision processes
neural network
sufficient conditions
special case

digital libraries
long run
information systems
stochastic shortest path
data sets