Integrating reinforcement learning with human demonstrations of varying ability.

Matthew E. Taylor Halit Bener Suay Sonia Chernova

Published in: AAMAS (2011)

Keyphrases

reinforcement learning
human beings
function approximation
cognitive abilities
optimal policy

markov decision processes
reinforcement learning algorithms
human interaction
key features
learning algorithm

database
state space
dynamic programming
human behavior
optimal control

learning process
temporal difference
neural network
data sets