Will it Blend? Composing Value Functions in Reinforcement Learning.

Benjamin van Niekerk Steven D. James Adam Christopher Earle Benjamin Rosman

Published in: CoRR (2018)

Keyphrases

reinforcement learning
function approximation
basis functions
machine learning
learning algorithm
multi agent
artificial neural networks
temporal difference
real time
databases
genetic algorithm
artificial intelligence
data structure
markov decision processes
reinforcement learning algorithms
autonomous learning