Login / Signup
Optimizing Long-term Predictions for Model-based Policy Search.
Andreas Doerr
Christian Daniel
Duy Nguyen-Tuong
Alonso Marco
Stefan Schaal
Marc Toussaint
Sebastian Trimpe
Published in:
CoRL (2017)
Keyphrases
</>
policy search
long term
reinforcement learning
reinforcement learning algorithms
continuous state
model free
continuous action
dynamic programming
reward function
neural network
machine learning
dynamic environments
partially observable markov decision processes
mobile robot
markov decision processes