Automatically Configuring Deep Q-Learning agents for the Berkeley Pacman project
Merino Pulido, Albert Eduard
MetadataShow full item record
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.
European research projects
The following license files are associated with this item:
Showing items related by title, author, creator and subject.
Pon Farreny, Josep (2014-09)The main goal of this project is to provide a distributed automatic configuration tool. In particular, we will extend the state-of-the-art automatic configuration tool GGA.
Orellana Trullols, Guillem (2019-07)Analitzar i estudiar diferents projectes de l’àmbit de ML per extreure’n les parts essencials amb la finalitat d’establir un cicle de desenvolupament genèric per a ser reutilitzat per tota mena de projectes del món de ...
Characterizing and unpacking learning to learn together skills in a wiki project in primary education Pifarré Turmo, Manoli; Li, Li (Elsevier, 2018)Learning to learn together (L2L2) skills are widely acknowledged as some of the most important 21 st century skills that enable learners to participate in a digital and global society. This paper examines how L2L2 skills ...