Proceedings of the 15th Belgium-Netherlands Conference on Artificial Intelligence pages:403-404
15th Belgian-Dutch Conference on Artificial Intelligence location:Nijmegen, The Netherlands date:October 23-24, 2003
Relational reinforcement learning (RRL) is a Q-learning technique which uses
first order regression techniques to generalize the Q-function.
Both the relational setting and the Q-learning context introduce a number
of difficulties which must be dealt with.
In this paper we investigate a few different methods that do incremental
relational instance based regression and can be used for RRL. This leads us
to different approaches which limit both memory consumption
and processing times. We implemented a number of these approaches and
experimentally evaluated and compared them to each other and an existing RRL
algorithm. These experiments show relational instance based regression to work
well and to add robustness to RRL.