DMCA
Creating Advice-Taking Reinforcement Learners (1996)
| Venue: | Machine Learning |
| Citations: | 115 - 10 self |
BibTeX
@INPROCEEDINGS{Maclin96creatingadvice-taking,
author = {Richard Maclin and Jude W. Shavlik and Pack Kaelbling},
title = {Creating Advice-Taking Reinforcement Learners},
booktitle = {Machine Learning},
year = {1996},
pages = {251--281}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
. Learning from reinforcements is a promising approach for creating intelligent agents. However, reinforcement learning usually requires a large number of training episodes. We present and evaluate a design that addresses this shortcoming by allowing a connectionist Q-learner to accept advice given, at any time and in a natural manner, by an external observer. In our approach, the advice-giver watches the learner and occasionally makes suggestions, expressed as instructions in a simple imperative programming language. Based on techniques from knowledge-based neural networks, we insert these programs directly into the agent's utility function. Subsequent reinforcement learning further integrates and refines the advice. We present empirical evidence that investigates several aspects of our approach and show that, given good advice, a learner can achieve statistically significant gains in expected reward. A second experiment shows that advice improves the expected reward regardless of the...
Keyphrases
advice-taking reinforcement learner utility function natural manner good advice advice-giver watch promising approach several aspect connectionist q-learner expected reward regardless subsequent reinforcement large number simple imperative programming language present empirical evidence intelligent agent significant gain knowledge-based neural network external observer second experiment show
