Using trajectory data to improve bayesian optimization for reinforcement learning.

Aaron Wilson Alan Fern Prasad Tadepalli

Published in: J. Mach. Learn. Res. (2014)

Keyphrases

trajectory data
reinforcement learning
moving objects
machine learning
information retrieval
optimization algorithm
learning algorithm
bayesian networks
optimization problems
space time
markov decision processes
moving object trajectories
spatial data
road network
traffic management