Deep active inference for pixel-based discrete control: evaluation on the car racing problem
Keywords
Loading...
Authors
Issue Date
2021-06-27
Language
en
Document type
Journal Title
Journal ISSN
Volume Title
Publisher
Title
ISSN
Volume
Issue
Startpage
Endpage
DOI
Abstract
Despite the potential of active inference for visual-based control,
learning the model and the preferences (priors) while interacting
with the environment is challenging. Here, we study the performance of
a deep active inference (dAIF) agent on OpenAI's car racing benchmark,
where there is no access to the car's state. The agent learns to encode
the world's state from high-dimensional input through unsupervised representation
learning. State inference and control are learned end-to-end
by optimizing the expected free energy. Results show that our model
achieves comparable performance to deep Q-learning. However, vanilla
dAIF does not reach state-of-the-art performance compared to other
world model approaches. Hence, we discuss the current model implementation's
limitations and potential architectures to overcome them.
Keywords: Deep Active Inference · Deep Learning · POMDP · Visualbased
Control
Note: This Bachelor Thesis has been written in paper format and has
been submitted to the 2021 International Workshop on Active Inference
(IWAI).
Description
Citation
Supervisor
Faculty
Faculteit der Sociale Wetenschappen