Closing the learning-planning loop with predictive state representations.

Byron Boots Sajid M. Siddiqi Geoffrey J. Gordon

Published in: Int. J. Robotics Res. (2011)

Keyphrases

predictive state representations
dynamical systems
learning algorithm
prior knowledge
search algorithm
active learning
learning tasks
temporal difference
machine learning
decision making
training data
supervised learning
heuristic search
domain independent
learning problems