Protecting against evaluation overfitting in empirical reinforcement learning.

Shimon Whiteson Brian Tanner Matthew E. Taylor Peter Stone

Published in: ADPRL (2011)

Keyphrases

reinforcement learning
cross validation
model free
multi agent
learning algorithm
artificial intelligence
decision trees
information retrieval
machine learning
state space
function approximation
evaluation model
data sets
website
case study
lower bound
upper bound
neural network
evaluation methods