Reinforcement Learning Transfer via Common Subspaces

Haitham Bou-Ammar, Matthew E. TaylorALA 2011 · OpenReview

Abstract

Agents in reinforcement learning tasks may learn slowly in large or complex tasks — transfer learning is one technique to speed up learning by providing an informative prior. How to best enable transfer between tasks with different state representations and/or actions is currently an open question. This paper introduces the concept of a common task subspace, which is used to autonomously learn how two tasks are related. Experiments in two different nonlinear domains empirically show that a learned inter-state mapping can successfully be used by fitted value iteration, to (1) improving the performance of a policy learned with a fixed number of samples, and (2) reducing the time required to converge to a (near-) optimal policy with unlimited samples.
BibTeX
@inproceedings{bouammar2011reinforcement,
  author = {Haitham Bou-Ammar and Matthew E. Taylor},
  title = {{Reinforcement Learning Transfer via Common Subspaces}},
  booktitle = {ALA},
  year = {2011},
  url = {https://openreview.net/forum?id=jEjCvnnY0s},
}

Loading related content...

Figure