Learning More from Less Data: Experiments with Lifelong Robot Learning

Sebastian Thrun and Joseph O'Sullivan

Recently, there has been an increased interest in ``lifelong'' machine learning methods that transfer knowledge across multiple learning tasks. Such methods have repeatedly found to outperform conventional, single-task learning algorithms when the learning tasks are appropriately related. To increase robustness of such approaches, methods are desirable that can reason about the relatedness of individual learning tasks, in order to avoid the danger arising from tasks that are unrelated and thus potentially misleading.

This paper describes the task-clustering (TC) algorithm. TC clusters learning tasks into classes of mutually related tasks. When facing a new thing to learn, TC first determines the most related task cluster, then exploits information selectively from this task cluster only. An empirical study carried out in a mobile robot domain shows that TC outperforms its non-selective counterpart in situations where only a small number of tasks is relevant.

Click here to obtain the full paper (316127 bytes).

@INPROCEEDINGS{Thrun96j,
  AUTHOR         = {S. Thrun and J. O'Sullivan},
  YEAR           = {1996},
  TITLE          = {Learning More From Less Data: Experiments in 
                    Lifelong Learning},
  BOOKTITLE      = {Seminar Digest},
  PUBLISHER      = {IEE}
}