Learning motions from demonstrations and rewards with time-invariant dynamical systems based policies
Sign Up to like & getrecommendations! Published in 2018 at "Autonomous Robots"
DOI: 10.1007/s10514-017-9636-y
Abstract: An important challenge when using reinforcement learning for learning motions in robotics is the choice of parameterization for the policy. We use Gaussian Mixture Regression to extract a parameterization with relevant non-linear features from a… read more here.
Keywords: learning motions; motions demonstrations; time invariant; time ... See more keywords