Book chapter
Learning Task Knowledge
pp.237-257
Strungmann Forum Reports, Mit Press
01 Jan 2018
Abstract
How does an agent acquire (i.e., learn) knowledge and information about a specific task by interacting with a teacher, so that ultimately the agent is able to execute the task successfully? This chapter reviews critical aspects of the learning process in interactive task learning (ITL). It discusses learning task knowledge through interaction, capabilities that facilitate learning, aspects of interaction that relate closely to learning, and evaluation dimensions and metrics for ITL systems. Given the interconnected nature of ITL, it also explores relationships between learning, knowledge, interaction, and tasks: how tasks influence learning, how knowledge should be represented, and what types of information and communication are needed to facilitate learning.
Metrics
4 Record Views
Details
- Title
- Learning Task Knowledge
- Creators
- Dario D. Salvucci - Drexel UniversityJohn E. Laird - Univ Michigan, CSE, Ann Arbor, MI 48109 USAFranklin Chang - Kobe City Univ Foreign Studies, Kobe, Hyogo, JapanKenneth D. Forbus - Northwestern Univ, EECS, Evanston, IL 60208 USAParisa Kordjamshidi - Tulane Univ, Comp Sci, New Orleans, LA 70118 USATom M. Mitchell - Carnegie Mellon Univ, Sch Comp Sci, Machine Learning Dept, Pittsburgh, PA 15213 USAShiwali Mohan - Palo Alto Res Ctr, Interact Analyt Lab, Palo Alto, CA 94304 USAMichael Spranger - Sony Comp Sci Labs Inc, Fundamental Res Lab, Tokyo 1410022, JapanSuzanne Stevenson - Univ Toronto, Dept Comp Sci, Toronto, ON M5S 3G4, CanadaAndrea Stocco - Univ Washington, Dept Psychol, Seattle, WA 98195 USAJ. Gregory Trafton - US Naval Res Lab, Washington, DC 20375 USA
- Contributors
- K A Gluck (Editor)J E Laird (Editor)
- Publication Details
- pp.237-257
- Series
- Strungmann Forum Reports
- Publisher
- Mit Press; CAMBRIDGE
- Number of pages
- 21
- Resource Type
- Book chapter
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Identifiers
- 991019170404704721
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Industry collaboration
- Domestic collaboration
- International collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Cybernetics
- Education & Educational Research
- Education, Scientific Disciplines
- Ergonomics
- Psychology, Educational