Online Skill Discovery using Graph-based Clustering
In Journal of Machine Learning Research, o.A., volume W&CP 24, pages 77-88, 2013.
We introduce a new online skill discovery method for reinforcement learning in discrete domains. The method is based on the bottleneck principle and identifies skills using a bottom-up hierarchical clustering of the estimated transition graph. In contrast to prior clustering approaches, it can be used incrementally and thus several times during the learning process. Our empirical evaluation shows that "assuming dense local connectivity in the face of uncertainty" can prevent premature identification of skills. Furthermore, we show that the choice of the linkage criterion is crucial for dealing with non-random sampling policies and stochastic environments.
Hierarchical Reinforcement Learning, Skill Discovery, Multi-task Learning