Loading [a11y]/accessibility-menu.js
Cooperative Navigation via Relational Graphs and State Abstraction | IEEE Journals & Magazine | IEEE Xplore

Cooperative Navigation via Relational Graphs and State Abstraction


Abstract:

We consider a cooperative-navigation problem in a partially observable MADRL framework. We investigate how agents cooperate to learn a communication protocol given a very...Show More

Abstract:

We consider a cooperative-navigation problem in a partially observable MADRL framework. We investigate how agents cooperate to learn a communication protocol given a very large state space while generalizing to a new environment. The proposed solution leverages the notion of structured observation and abstraction, in which the raw-pixel observations are converted into a relational graph that is then used for learning abstraction. Abstraction is performed based on compression using a relational graph autoencoder (RGAE) and a multilayer perceptron (MLP) to remove irrelevant information. The results show the effectiveness of the proposed MLP and RGAE in learning better policies with better generalization capabilities. It is also shown that communication among agents is instrumental in improving the navigation task performance.
Published in: IEEE Networking Letters ( Volume: 5, Issue: 4, December 2023)
Page(s): 184 - 188
Date of Publication: 12 June 2023
Electronic ISSN: 2576-3156

Funding Agency:


References

References is not available for this document.