TY - GEN
T1 - Advice taking and transfer learning
T2 - 2008 AAAI Fall Symposium
AU - Torrey, Lisa
AU - Walker, Trevor
AU - Maclin, Richard
AU - Shavlik, Jude
PY - 2008/12/1
Y1 - 2008/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=77952176586&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77952176586&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77952176586
SN - 9781577353980
T3 - AAAI Fall Symposium - Technical Report
SP - 103
EP - 110
BT - Naturally-Inspired Artificial Intelligence - Papers from the AAAI Fall Symposium, Technical Report
Y2 - 7 November 2008 through 9 November 2008
ER -