Skip to content. | Skip to navigation

Personal tools
Document Actions

G D Konidaris and A G Barto (2009)

Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining

In: Advances in Neural Information Processing Systems 22 (NIPS '09), ed. by Y. Bengio, D. Schuurmans, J. Lafferty, C.K.I. Williams, A. Culotta , pp. 1015-1023.

We introduce a skill discovery method for reinforcement learning in continuous domains that constructs chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates appropriate skills and achieves perfor- mance benefits in a challenging continuous domain.