Authors:
Juan M. Montoya
and
Christian Borgelt
Affiliation:
Chair for Bioinformatics and Information Mining, University of Konstanz and Germany
Keyword(s):
Wide and Deep Reinforcement Learning, Wide Deep Q-Networks, Value Function Approximation, Reinforcement Learning Agents.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Evolutionary Computing
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Symbolic Systems
;
Theory and Methods
Abstract:
For the last decade Deep Reinforcement Learning has undergone exponential development; however, less has
been done to integrate linear methods into it. Our Wide and Deep Reinforcement Learning framework provides
a tool that combines linear and non-linear methods into one. For practical implementations, our framework can
help integrate expert knowledge while improving the performance of existing Deep Reinforcement Learning
algorithms. Our research aims to generate a simple practical framework to extend such algorithms. To test
this framework we develop an extension of the popular Deep Q-Networks algorithm, which we name Wide
Deep Q-Networks. We analyze its performance compared to Deep Q-Networks and Linear Agents, as well as
human players. We apply our new algorithm to Berkley’s Pac-Man environment. Our algorithm considerably
outperforms Deep Q-Networks’ both in terms of learning speed and ultimate performance showing its potential
for boosting existing algorithms.