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

Alberto Archetti Marco Cannici Matteo Matteucci

Published in: LOD (2021)

Keyphrases

learning algorithm
learning systems
reinforcement learning
unsupervised learning
learning tasks
learning process
control knowledge
motor control
neural network
mobile robot
online learning
random walk
feed forward
graph theory
learning rules