ERIC Number: EJ1057812
Record Type: Journal
Publication Date: 2015-Apr
Abstractor: As Provided
Reference Count: N/A
Inferring Learners' Knowledge from Their Actions
Rafferty, Anna N.; LaMar, Michelle M.; Griffiths, Thomas L.
Cognitive Science, v39 n3 p584-618 Apr 2015
Watching another person take actions to complete a goal and making inferences about that person's knowledge is a relatively natural task for people. This ability can be especially important in educational settings, where the inferences can be used for assessment, diagnosing misconceptions, and providing informative feedback. In this paper, we develop a general framework for automatically making such inferences based on observed actions; this framework is particularly relevant for inferring student knowledge in educational games and other interactive virtual environments. Our approach relies on modeling action planning: We formalize the problem as a Markov decision process in which one must choose what actions to take to complete a goal, where choices will be dependent on one's beliefs about how actions affect the environment. We use a variation of inverse reinforcement learning to infer these beliefs. Through two lab experiments, we show that this model can recover people's beliefs in a simple environment, with accuracy comparable to that of human observers. We then demonstrate that the model can be used to provide real-time feedback and to model data from an existing educational game.
Descriptors: Inferences, Knowledge Level, Educational Games, Computer Simulation, Models, Planning, Markov Processes, Beliefs, Reinforcement, Accuracy, Feedback (Response)
Wiley-Blackwell. 350 Main Street, Malden, MA 02148. Tel: 800-835-6770; Tel: 781-388-8598; Fax: 781-388-8232; e-mail: email@example.com; Web site: http://www.wiley.com/WileyCDA
Publication Type: Journal Articles; Reports - Descriptive
Education Level: N/A
Sponsor: US Department of Defense; National Science Foundation
Authoring Institution: N/A
IES Grant or Contract Numbers: IIS-0845410|DRL-0816359