Title
Learning In Context: Enhancing Machine Learning With Context-Based Reasoning
Keywords
Context-based reasoning; Learning from demonstration; Learning from imitation; Machine learning from observation
Abstract
This article describes how an experiment to train an agent to perform a task, which had originally failed, was made successful by incorporating a contextual structure that decomposed the tasks into contexts through Context-based Reasoning. The task involved a simulation of a crane that was used by a human operator to move boxes from arbitrary locations throughout a wide area to a designated drop off location in the environment. Initial attempts to teach an agent how to perform the task through observation in a context-free manner yielded poor performance. However, when the task to be learned was decomposed into separate contexts and the agents learned each context independently, the performance improved significantly. The paper describes the process that enabled the improvements achieved and discusses the tests and results that demonstrated the improvement.
Publication Date
9-18-2014
Publication Title
Applied Intelligence
Volume
41
Issue
3
Number of Pages
709-724
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1007/s10489-014-0550-0
Copyright Status
Unknown
Socpus ID
84918829113 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84918829113
STARS Citation
Stein, Gary and Gonzalez, Avelino J., "Learning In Context: Enhancing Machine Learning With Context-Based Reasoning" (2014). Scopus Export 2010-2014. 8036.
https://stars.library.ucf.edu/scopus2010/8036