Hyperparameter Selection in Reinforcement Learning Using the "Design of Experiments" Method.

Mark C. McKenzie Mark D. McDonnell

Published in: INNS DLIA@IJCNN (2023)

Keyphrases

reinforcement learning
high precision
detection method
experimental evaluation
preprocessing
significant improvement
model free
synthetic data
computational cost
model selection
pairwise
selection strategy
neural network
dynamic programming
similarity measure
case study
prior information