Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning☆.
Parvin MalekzadehMing HouKonstantinos N. PlataniotisPublished in: Neurocomputing (2023)
Keyphrases
- reinforcement learning
- transfer learning
- model free
- previously learned
- transferring knowledge
- function approximation
- state space
- partial observability
- knowledge transfer
- dynamic programming
- real robot
- multiple tasks
- learning algorithm
- transfer knowledge
- image features
- supervised learning
- learning tasks
- data sets
- reinforcement learning algorithms
- robotic control
- neural network