Part of Advances in Neural Information Processing Systems 16 (NIPS 2003)
H. Kim, Michael Jordan, Shankar Sastry, Andrew Ng
Autonomous helicopter flight represents a challenging control problem, with complex, noisy, dynamics. In this paper, we describe a successful application of reinforcement learning to autonomous helicopter flight. We first fit a stochastic, nonlinear model of the helicopter dynamics. We then use the model to learn to hover in place, and to fly a number of maneuvers taken from an RC helicopter competition.