Learning Trajectory Preferences for Manipulators via Iterative Improvement.

Ashesh Jain Brian Wojcik Thorsten Joachims Ashutosh Saxena

Published in: NIPS (2013)

Keyphrases

online learning
learning process
learning systems
reinforcement learning
active learning
prior knowledge
unsupervised learning
user preferences
learning tasks
incremental learning
machine learning
learning algorithm
e learning
background knowledge
learning problems