Login / Signup
Learning motions from demonstrations and rewards with time-invariant dynamical systems based policies.
Joel Rey
Klas Kronander
Farbod Farshidian
Jonas Buchli
Aude Billard
Published in:
Auton. Robots (2018)
Keyphrases
</>
dynamical systems
predictive state representations
reinforcement learning
reinforcement learning methods
learning algorithm
connectionist networks
dynamic systems
learning tasks
partially observable
nonlinear dynamical systems
image sequences
optimal solution
partially observable markov decision processes