This talk covers:

• Self-modifying policies that can learn their own probabilistic learning algorithm: Learning to learn

• Application to complex toy problem

• Mostly pictures! To better understand, download the following papers:

• J. Schmidhuber, J. Zhao, N. Schraudolph. Reinforcement learning with self-modifying policies. In Learning to learn, Kluwer, pages 293-309, 1997.

• J. Schmidhuber, J. Zhao, and M. Wiering. Machine Learning 28:105-130, 1997.

• M. Wiering and J. Schmidhuber. Solving POMDPs using Levin search and EIRA. ICML 1996, pages 534-542

Previous slide

Next slide

Back to first slide

View graphic version