Next: ACKNOWLEDGEMENTS
Up: CURIOUS MODEL-BUILDING CONTROL SYSTEMS
Previous: EXPERIMENTS
The central idea of this paper is to construct an adaptive system
which learns to predict the effects of further learning. This is
done by training an adaptive sub-module to predict (the expectation
of the sum of)
future error changes
caused by a particular learning algorithm. Here one adaptive module
learns to make estimates about the effects of the learning procedure of another
adaptive module. In other words, there is a module
which learns to make a statement
about learning itself. This is related to the concept
of `meta-learning':
In a very limited sense the system learns how to learn.
The method represents a general
strategy for learning to select training examples such that the
expected performance improvement is maximized. Therefore the usefulness
of the approach is not limited to model-building control systems.
The principles above are general enough to be of interest
whenever the task is to select appropriate
training examples for any kind of learning system.
Juergen Schmidhuber
2003-02-28
Back to Active Learning - Exploration - Curiosity page
Back to Reinforcement Learning page