Login / Signup
Multi-Step Dyna Planning for Policy Evaluation and Control.
Hengshuai Yao
Richard S. Sutton
Shalabh Bhatnagar
Diao Dongcui
Csaba Szepesvári
Published in:
NIPS (2009)
Keyphrases
</>
multi step
td learning
policy evaluation
temporal difference
function approximation
action selection
least squares
knn
neural network
planning problems
policy iteration
decision trees
k nearest neighbor
monte carlo
model free