TraKDis: A Transformer-based Knowledge Distillation Approach for Visual Reinforcement Learning with Application to Cloth Manipulation.
Wei ChenNicolas RojasPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- knowledge acquisition
- domain knowledge
- visual representations
- fuzzy logic
- knowledge management
- optimal control
- function approximation
- learning systems
- real time
- prior knowledge
- artificial intelligence
- machine learning
- knowledge representation
- multi agent systems
- knowledge based systems
- higher level
- visual features
- design process
- multi agent
- domain experts
- fault diagnosis
- image processing