Login / Signup
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards.
Falcon Z. Dai
Matthew R. Walter
Published in:
NeurIPS (2019)
Keyphrases
</>
reward function
high cost
markov chain
cost reduction
opportunity cost
control policy
reinforcement learning
neural network
objective function
cost function
cost sensitive
case study
expected cost
databases
wireless sensor networks
dynamic programming
markov decision processes
decision making
average cost
data sets