Neural Weighted A*: Learning Graph Costs and Heuristics with Differentiable Anytime A.

Alberto Archetti Marco Cannici Matteo Matteucci

Published in: CoRR (2021)

Keyphrases

learning process
reinforcement learning
learning algorithm
objective function
active learning
weighted graph
learning rules
neural network
online learning
prior knowledge
supervised learning
random walk
learning systems
recurrent networks
macro operators