Login / Signup
Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning.
Luca Biferale
Fabio Bonaccorso
Michele Buzzicotti
Patricio Clark Di Leoni
Kristian Gustavsson
Published in:
CoRR (2019)
Keyphrases
</>
reinforcement learning
dynamic programming
optimal control
real time
optimal solution
state space
data sets
function approximation
navigation systems
learning process
supervised learning
closed form
optimal design
robot navigation