Cooperative Navigation via Relational Graphs and State Abstraction
Mostafa, Salwa; Abdel-Aziz, Mohamed K.; Bennis, Mehdi (2023-06-12)
IEEE
12.06.2023
S. Mostafa, M. K. Abdel-Aziz and M. Bennis, "Cooperative Navigation via Relational Graphs and State Abstraction," in IEEE Networking Letters, vol. 5, no. 4, pp. 184-188, Dec. 2023, doi: 10.1109/LNET.2023.3285295
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202403152239
https://urn.fi/URN:NBN:fi:oulu-202403152239
Tiivistelmä
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.
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.
Kokoelmat
- Avoin saatavuus [34513]