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, 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
Back to J. Schmidhuber's Metalearning page