Randomized function fitting-based empirical value iteration.

William B. Haskell Pengqian Yu Hiteshi Sharma Rahul Jain

Published in: CDC (2017)

Keyphrases

machine learning
markov decision processes
theoretical analysis
state space
real time
dynamic programming
search algorithm
heuristic search
information theoretic
information retrieval
search space
lower bound
image segmentation
parameter estimation
parametric models
piecewise linear
residual errors