Skill acquisition via transfer learning and advice taking

DMCA

Skill acquisition via transfer learning and advice taking (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Lisa Torrey , Jude Shavlik , Trevor Walker , Richard Maclin

Venue:	In Proceedings of the 17th European Conference on Machine Learning
Citations:	25 - 3 self

BibTeX

@INPROCEEDINGS{Torrey06skillacquisition,
    author = {Lisa Torrey and Jude Shavlik and Trevor Walker and Richard Maclin},
    title = {Skill acquisition via transfer learning and advice taking},
    booktitle = {In Proceedings of the 17th European Conference on Machine Learning},
    year = {2006},
    pages = {425--436},
    publisher = {Springer}
}

OpenURL

Abstract

Abstract. We describe a reinforcement learning system that transfers skills from a previously learned source task to a related target task. The system uses inductive logic programming to analyze experience in the source task, and transfers rules for when to take actions. The target task learner accepts these rules through an advice-taking algorithm, which allows learners to benefit from outside guidance that may be imperfect. Our system accepts a human-provided mapping, which specifies the similarities between the source and target tasks and may also include advice about the differences between them. Using three tasks in the RoboCup simulated soccer domain, we demonstrate that this system can speed up reinforcement learning substantially. 1

Keyphrases

advice taking transfer learning skill acquisition source task related target task transfer rule advice-taking algorithm target task learner outside guidance soccer domain human-provided mapping inductive logic target task

DMCA