Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning.
Kaiqi ChenYong LeeHarold SohPublished in: ICRA (2021)
Keyphrases
- multi modal
- mutual information
- reinforcement learning
- multi modality
- information theoretic
- cross modal
- semantic concepts
- information gain
- feature extraction
- audio visual
- similarity measure
- video search
- particle filter
- fusing multiple
- image annotation
- machine learning
- image registration
- state space
- low level
- high dimensional
- learning algorithm