An Automated Measure of MDP Similarity for Transfer in Reinforcement Learning

  title={An Automated Measure of MDP Similarity for Transfer in Reinforcement Learning},
  author={Haitham Bou Ammar and Eric Eaton and Gerhard Weiss Kurt Driessens and Karl Tuyls and Decebal Mocanu Matthew Taylor},
Transfer learning can improve the reinforcement learning of a new task by allowing the agent to reuse knowledge acquired from other source tasks. Despite their success, transfer learning methods rely on having relevant source tasks; transfer from inappropriate tasks can inhibit performance on the new task. For fully autonomous transfer, it is critical to have a method for automatically choosing relevant source tasks, which requires a similarity measure between Markov Decision Processes (MDPs… CONTINUE READING
Highly Cited
This paper has 26 citations. REVIEW CITATIONS


Publications referenced by this paper.
Showing 1-10 of 14 references

Reinforcement Learning and Dynamic Programming Using Function Approximators

  • L. Buşoniu, R. Babuška, B. De Schutter, D. Ernst
  • Boca Raton, Florida: CRC Press.
  • 2010
1 Excerpt

Learning deep architectures for AI

  • Y. Bengio
  • Foundations and Trends in Machine Learning 2(1):1…
  • 2009
1 Excerpt

Similar Papers

Loading similar papers…