Login / Signup
Improving Real-Time Bidding Using a Constrained Markov Decision Process.
Manxing Du
Redouane Sassioui
Georgios Varisteas
Radu State
Mats Brorsson
Omar Cherkaoui
Published in:
ADMA (2017)
Keyphrases
</>
markov decision process
real time
optimal policy
state space
markov decision processes
reinforcement learning
transition matrices
finite horizon
control system
infinite horizon
initial state
multi agent
graphical models