next up previous
Next: Reinforcement Learning and Adaptive Up: Introduction Previous: Models of Optimal Behavior

Measuring Learning Performance

The criteria given in the previous section can be used to assess the policies learned by a given algorithm. We would also like to be able to evaluate the quality of learning itself. There are several incompatible measures in use.


next up previous
Next: Reinforcement Learning and Adaptive Up: Introduction Previous: Models of Optimal Behavior

Leslie Pack Kaelbling
Wed May 1 13:19:13 EDT 1996