Login / Signup
Dynamic Programming and Value-Function Approximation in Sequential Decision Problems: Error Analysis and Numerical Results.
Mauro Gaggero
Giorgio Gnecco
Marcello Sanguineti
Published in:
J. Optim. Theory Appl. (2013)
Keyphrases
</>
error analysis
dynamic programming
sequential decision problems
reinforcement learning
state space
least squares
error correction
cross ratio
temporal difference
active exploration
basis functions
sensitivity analysis
data collection
stereo matching
optimal control
infinite horizon
markov decision problems