Login / Signup
Exploiting the Structural Properties of the Underlying Markov Decision Problem in the Q-Learning Algorithm.
Sumit Kunnumkal
Huseyin Topaloglu
Published in:
INFORMS J. Comput. (2008)
Keyphrases
</>
structural properties
learning algorithm
markov decision problems
reinforcement learning
training data
supervised learning
linear programming
learning process
decision processes
neural network
machine learning
decision making
optimal policy
learning agent