Learning to Predict Variable-Delay Rewards and Its Role in Autonomous Developmental Robotics.

Andrés Pérez-Uribe Michèle Courant

Published in: IWANN (2) (2001)

Keyphrases

learning algorithm
learning process
artificial intelligence
reinforcement learning
computer vision
robot control
online learning
autonomous learning
learning scheme
learning problems
neural network
quality of service
unsupervised learning
robotic systems
supervised learning
support vector
perception action