Efficient Reinforcement Learning for Motor Control
Marc Deisenroth and Carl Edward Rasmussen
In: 10th International PhD Workshop on Systems and Control, 22-26 September 2009, Czech Republic.
Artificial learners often require many more trials than humans or
animals when learning motor control tasks in the absence of expert
knowledge. We implement two key ingredients of biological learning
systems, generalization and incorporation of uncertainty into the
decision-making process, to speed up artificial learning. We present
a coherent and fully Bayesian framework that allows for efficient
artificial learning in the absence of expert knowledge. The success
of our learning framework is demonstrated on challenging nonlinear
control problems in simulation and in hardware.