A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning.
Adrien BanseVenkatraman RenganathanRaphaël M. JungersPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- transfer learning
- reinforcement learning
- state space
- finite state
- optimal policy
- policy iteration
- knowledge transfer
- transition matrices
- cross domain
- learning tasks
- text classification
- machine learning
- labeled data
- infinite horizon
- text categorization
- dynamic programming
- active learning
- decision theoretic planning
- neural network
- domain specific
- feature space
- structure learning
- reinforcement learning algorithms