|
Title:
|
Automatically Configuring Deep Q-Learning agents for the Berkeley Pacman project
|
|
Author:
|
Merino Pulido, Albert Eduard
|
|
Other authors:
|
Ansótegui Gil, Carlos José; Universitat de Lleida. Escola Politècnica Superior |
|
Notes:
|
Recently, there have been several advances on integrating Deep Neural
Networks (DNNs) and Reinforcement Learning (RL) algorithms. These
efforts led to the development of Deep Q-Learning (DQL) algorithms
which have been applied successfully to develop competitive approaches for
multiagent games. Both DNNs and RL algorithms are highly parameterized
and di erent settings can have a dramatic impact on their e ciency. Thus,
DQL algorithms can also greatly bene t from a good setting of their
parameters. In this project, we show how to apply Automatic Con guration
(AC) tools in order to explore efficiently the parameter search space. We
have conducted an extensive experimental investigation in the Berkeley
Pacman environment which con rms that AC tools can provide up to an
additional 20% boost in performance to DQL agents. |
|
Subject(s):
|
-Automatic configuration
-Reinforcement learning
-Deep Q-learning
-Aprenentatge automàtic |
|
Rights:
|
cc-by-nc-nd
http://creativecommons.org/licenses/by-nc-nd/4.0/
|
|
Document type:
|
Research/Master Thesis |
|
Share:
|
|
