Fine-tuning Deep Reinforcement Learning Policies with r-STDP for Domain Adaptation.
Mahmoud AklYulia SandamirskayaDeniz ErgeneFlorian WalterAlois C. KnollPublished in: ICONS (2022)
Keyphrases
- fine tuning
- domain adaptation
- reinforcement learning
- optimal policy
- transfer learning
- cross domain
- multiple sources
- semi supervised
- target domain
- labeled data
- semi supervised learning
- test data
- supervised learning
- fine tuned
- manifold alignment
- learning tasks
- covariate shift
- learning algorithm
- learning process
- training data
- unlabeled data
- active learning
- co training
- document classification
- text classification
- prior knowledge
- learning environment
- decision trees
- data mining