Q-Learning to navigate turbulence without a map.

Marco Rando Martin James Alessandro Verri Lorenzo Rosasco Agnese Seminara

Published in: CoRR (2024)

Keyphrases

learning algorithm
reinforcement learning
cooperative
function approximation
multi agent
model free
reinforcement learning algorithms
stochastic approximation
state space
maximum a posteriori
long range
action selection
database
neural network
atmospheric turbulence