Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining

Part of Advances in Neural Information Processing Systems 22 (NIPS 2009)

Bibtex Metadata Paper Supplemental


George Konidaris, Andrew Barto


We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains, that builds chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates skills that result in performance benefits in a challenging continuous domain.