Learning from Demonstration Using MDP Induced Metrics.

Francisco S. Melo Manuel Lopes

Published in: ECML/PKDD (2) (2010)

Keyphrases

markov decision processes
reinforcement learning
state space
optimal policy
utility function
markov decision process
linear program
finite state
search algorithm
dynamic programming algorithms
neural network
search engine
similarity measure
natural language
similarity metrics
factored mdps