Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning.
Parvin MalekzadehMing HouKonstantinos N. PlataniotisPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- transfer learning
- model free
- previously learned
- transferring knowledge
- feature vectors
- learning algorithm
- state space
- reinforcement learning agents
- partial observability
- learning tasks
- function approximation
- knowledge transfer
- optimal policy
- multi agent
- multi task
- multi task learning
- machine learning
- active learning
- feature selection
- multiple tasks
- decision making
- decision theory
- uncertain data
- markov decision processes
- image features
- dynamic programming