Advice taking and transfer learning: Naturally inspired extensions to reinforcement learning

Lisa Torrey, Trevor Walker, Richard Maclin, Jude Shavlik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Reinforcement learning (RL) is a machine learning technique with strong links to natural learning. However, it shares several "unnatural" limitations with many other successful machine learning algorithms. RL agents are not typically able to take advice or to adjust to new situations beyond the specific problem they are asked to learn. Due to limitations like these, RL remains slower and less adaptable than natural learning. Our recent work focuses on extending RL to include the naturally inspired abilities of advice taking and transfer learning. Through experiments in the RoboCup domain, we show that doing so can make RL faster and more adaptable.

Original languageEnglish (US)
Title of host publicationNaturally-Inspired Artificial Intelligence - Papers from the AAAI Fall Symposium, Technical Report
Pages103-110
Number of pages8
StatePublished - Dec 1 2008
Externally publishedYes
Event2008 AAAI Fall Symposium - Arlington, VA, United States
Duration: Nov 7 2008Nov 9 2008

Publication series

NameAAAI Fall Symposium - Technical Report
VolumeFS-08-06

Other

Other2008 AAAI Fall Symposium
CountryUnited States
CityArlington, VA
Period11/7/0811/9/08

Fingerprint Dive into the research topics of 'Advice taking and transfer learning: Naturally inspired extensions to reinforcement learning'. Together they form a unique fingerprint.

  • Cite this

    Torrey, L., Walker, T., Maclin, R., & Shavlik, J. (2008). Advice taking and transfer learning: Naturally inspired extensions to reinforcement learning. In Naturally-Inspired Artificial Intelligence - Papers from the AAAI Fall Symposium, Technical Report (pp. 103-110). (AAAI Fall Symposium - Technical Report; Vol. FS-08-06).