Login / Signup
Walking Motion Learning of Quadrupedal Walking Robot by Profit Sharing That Can Learn Deterministic Policy for POMDPs Environments.
Yuya Morino
Yuko Osana
Published in:
SEAL (2014)
Keyphrases
</>
reinforcement learning
walking robot
learning algorithm
profit sharing
image sequences
state space
markov chain
partially observable
partially observable markov decision processes
decision making
information sharing
policy gradient
policy search
policy gradient methods