Multi-cost Bounded Reachability in MDP.

Arnd Hartmanns Sebastian Junges Joost-Pieter Katoen Tim Quatmann

Published in: TACAS (2) (2018)

Keyphrases

state space
average cost
markov decision process
total cost
cost reduction
high cost
markov decision processes
cost sensitive
database
optimal policy
reinforcement learning
communication cost
finite state
optimal solution
transitive closure
learning algorithm
neural network