Back to Search
Start Over
Transfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling.
- Source :
- Machine Learning: ECML 2007; 2007, p699-707, 9p
- Publication Year :
- 2007
-
Abstract
- We investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a new incremental relational regression tree algorithm that is capable of dealing with concept drift through tree restructuring and show that it enables a Q-learner to transfer knowledge from one task to another by recycling those parts of the generalized Q-function that still hold interesting information for the new task. We illustrate the performance of the algorithm in several experiments. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISBNs :
- 9783540749578
- Database :
- Complementary Index
- Journal :
- Machine Learning: ECML 2007
- Publication Type :
- Book
- Accession number :
- 33170081
- Full Text :
- https://doi.org/10.1007/978-3-540-74958-5_70