Abstract: |
In reinforcement learning problems it has been considered that neither exploitation nor exploration can be pursued exclusively without failing at the task. The optimal balance between exploring and exploiting changes as the training progresses due to the increasing amount of learnt knowledge. This shift in balance is not known a priori so an autonomous online adjustment is sought. Human beings manage this balance through logic and explorations based on feedback from the environment. The XCS learning classifier system uses a fixed explore/exploit balance, but does keep multiple statistics about its performance and interaction in an environment. Utilising these statistics in a non-linear manner, autonomous adjustment of the explore/exploit balance was achieved. This resulted in reduced exploration in simple environments, which could increase with the complexity of the problem domain. It also prevented unsuccessful 'loop' exploit trials and suggests a method of dynamic choice in goal setting. |
