Real-time individualized training vectors for experiential learning

Report

Military training utilizing serious games or virtual worlds potentially generate data that can be mined to better understand how trainees’ learn in experiential exercises. Few data mining approaches for deployed military training games exist. Opportunities exist to collect and analyze these data, as well as to construct a fullhistory learner model. Outcomes discussed in the present document include results from a quasi-experimental research study on military game-based experiential learning, the deployment of an online game for training evidence collection, and results from a proof-of-concept pilot study on the development of individualized training vectors. This Lab Directed Research & Development (LDRD) project leveraged products within projects, such as Titan (Network Grand Challenge), RealTime Feedback and Evaluation System, (America’s Army Adaptive Thinking & Leadership, DARWARS Ambush! NK), and Dynamic Bayesian Networks to investigate whether machine learning capabilities could perform real-time, in-game similarity vectors of learner performance, toward adaptation of content delivery, and quantitative measurement of experiential learning.

Authors: Raybourn, E; Fabian, N; Glickman, M; Tucker, E; Willis, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Sandia National Laborotories
• Journal: Real-time individualized training vectors for experiential learning
• Publication date: 2011-01-01
• Keywords: SBTMR