Bayesian reinforcement learning in continuous POMDPs with application to robot navigation.

Stéphane Ross Brahim Chaib-draa Joelle Pineau

Published in: ICRA (2008)

Keyphrases

robot navigation
bayesian reinforcement learning
continuous state
autonomous mobile robot
computer vision
reinforcement learning
autonomous robots
scene understanding
dynamic programming
linear programming
sufficient conditions
optimal policy
partially observable markov decision processes