Login / Signup
On Policy Iteration as a Newton s Method and Polynomial Policy Iteration Algorithms.
Omid Madani
Published in:
AAAI/IAAI (2002)
Keyphrases
</>
policy iteration
model free
markov decision processes
reinforcement learning
policy evaluation
fixed point
convergence rate
least squares
sample path
computational complexity
optimal policy
graphical models
basis functions
dynamic programming
cost function
objective function
image sequences