Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning.

Faustino J. Gomez Julian Togelius Jürgen Schmidhuber

Published in: ICANN (2) (2009)

Keyphrases

reinforcement learning
genetic algorithm
evolutionary computation
function approximation
real world
worst case
markov decision processes
reinforcement learning algorithms
evolutionary optimization
information systems
case study
multi agent
learning process
dynamic programming
optimal policy
evolutionary methods