Adaptive Bases for Reinforcement Learning.

Dotan Di Castro Shie Mannor

Published in: ECML/PKDD (1) (2010)

Keyphrases

reinforcement learning
function approximation
state space
model free
data sets
neural network
adaptive learning
genetic algorithm
decision trees
case study
multi agent
dynamic programming
basis functions
markov decision processes
reinforcement learning algorithms
learning capabilities