Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NB3PPR5Mrecord.jsonopen to challenge →
read the original abstract
This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared representation between modalities; this can cause poor performance on downstream tasks and over-reliance on specific sensors. As a solution, we contribute a new multi-modal deep latent state-space model, trained using a mutual information lower-bound. The key innovation is a specially-designed density ratio estimator that encourages consistency between the latent codes of each modality. We tasked our method to learn policies (in a self-supervised manner) on multi-modal Natural MuJoCo benchmarks and a challenging Table Wiping task. Experiments show our method significantly outperforms state-of-the-art deep reinforcement learning methods, particularly in the presence of missing observations.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.