Discrete-Valued Neural Communication

The dataset used in the paper is a visual reasoning task using Graph Neural Networks (GNNs) and Recurrent Independent Mechanisms (RIMs). The dataset consists of 8 Atari games and 3D shapes environment. The dataset is used to evaluate the performance of the Discrete-Valued Neural Communication (DVNC) method.

Data and Resources

Cite this as

Dianbo Liu, Alex Lamb, Kenji Kawaguchi, Anirudh Goyal, Chen Sun, Michael Curtis Mozer, Yoshua Bengio (2024). Dataset: Discrete-Valued Neural Communication. https://doi.org/10.57702/awnuwq98

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2107.02367
Author Dianbo Liu
More Authors
Alex Lamb
Kenji Kawaguchi
Anirudh Goyal
Chen Sun
Michael Curtis Mozer
Yoshua Bengio