Autonomous Inverted Helicopter Flight via Reinforcement Learning.

Andrew Y. Ng Adam Coates Mark Diel Varun Ganapathi Jamie Schulte Ben Tse Eric Berger Eric Liang

Published in: ISER (2004)

Keyphrases

flight data
reinforcement learning
autonomous learning
unmanned aerial vehicles
flight test
function approximation
learning capabilities
learning algorithm

reinforcement learning algorithms
state space
temporal difference
parameter identification
function approximators
machine learning
policy search
space shuttle

robotic control
real time
autonomous mental development
autonomous navigation
optimal control
markov decision processes
mathematical model
nasa langley research center

air traffic control
transition model
model free
closed loop
flight path
civil aviation
supervised learning