Model-Based Reinforcement Learning in a Complex Domain.

Shivaram Kalyanakrishnan Peter Stone Yaxin Liu

Published in: RoboCup (2007)

Keyphrases

complex domains
model based reinforcement learning
reinforcement learning
markov decision processes
domain theory
bayesian networks
machine learning
pairwise
artificial intelligence
active learning
state space
optimal policy
finite state
partially observable
relational domains