Value targets in off-policy AlphaZero: a new greedy backup.

Daniel Willemsen Hendrik Baier Michael Kaisers

Published in: Neural Comput. Appl. (2022)

Keyphrases

greedy algorithm
search algorithm
dynamic programming
target detection
high availability
feature selection
locally optimal
greedy strategy
search space
target tracking
website
multi target
real time
data sets
greedy heuristic