A Perceived Environment Design using a Multi-Modal Variational Autoencoder for learning Active-Sensing
arXiv:1911.00584v11 citations
Originality Synthesis-oriented
AI Analysis
This work addresses the challenge of active sensing in robotics or AI agents, but appears incremental as it builds on existing multi-modal VAE and curiosity-driven methods.
The paper tackled the problem of designing a perceived environment for agents using a multi-modal variational autoencoder, resulting in a framework that integrates sensory data and action spaces, and compared it to curiosity-driven learning approaches.
This contribution comprises the interplay between a multi-modal variational autoencoder and an environment to a perceived environment, on which an agent can act. Furthermore, we conclude our work with a comparison to curiosity-driven learning.