MLKD logo   Machine Learning &
Knowledge Discovery Group

Transfer Learning for RL Domains


Transfer learning refers to the process of conveying experience from a simple task to another more complex (and related) task in order to reduce the amount of time that is required to learn the latter task. Typically, in a transfer learning procedure the agent learns a behavior in a source task, and it uses the gained knowledge in order to speed up the learning process in a target task. Reinforcement Learning algorithms are time expensive when they learn from scratch, especially in complex domains, and transfer learning comprises a suitable solution to speed up the training process.

Source Code

Here you can find our transfer learning algorithm for the Mountain Car Domain.

The software is distributed under the GNU GPL licence. It requires RL-Glue 3.0 and tile coding. Please contact Ioannis Partalas for bug reports, comments, suggestions or request for help with the source code.

Source code developers: Ioannis Partalas.


  • Fachantidis, A., Partalas, I., Taylor, M., & Vlahavas, I., “Autonomous Selection of Inter-Task Mappings in Transfer Learning (extended abstract)”, Proc. AAAI Spring Symposium Lifelong Machine Learning, Stanford, U.S.A, 2013 (accepted for presentation)
  • Fachantidis, A., Partalas, I., Tsoumakas, G., & Vlahavas, I., “Transferring task models in reinforcement learning agents”. Neurocomputing, Elsevier, 2013 (to be published)
  • Fachantidis, A., Partalas, I., Taylor, M., & Vlahavas, I, “Transfer learning via multiple inter-task mappings", 9th European Workshop on Reinforcement Learning (EWRL 2012), Athens, Greece, Recent Advances in Reinforcement Learning, Lecture Notes in Computer Science, pp. 225–236, 2012
  • Fachantidis, A., Partalas, I., Tsoumakas, G., & Vlahavas, I. “Transferring models in hybrid reinforcement learning agents”, Proc. Engineering Applications of Neural Networks (EANN 2011), Corfu, Greece, IFIP Advances in Information and Communication Technology. Springer Boston, pp. 162–171, 2011.
  • I. Partalas, G. Tsoumakas, K. Tzevanidis, I. Vlahavas, "Transerring Experience in Reinforcement Learning through Task Decomposition", Proc. 8th International Conferences on Autonomous Agents and Multiagent Systems (AAMAS 2009), Budapest, Hungary,2009.