Building High-Performing Human-Like Tactical Agents Through Observation and Experience

    Authors

    G. Stein;A. J. Gonzalez

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    IEEE Trans. Syst. Man Cybern. Part B-Cybern.

    Keywords

    Experiential learning; FALCONET; haptics; machine learning; multimodal; observational learning; PIGEON; NEURAL NETWORKS; Automation & Control Systems; Computer Science, Artificial Intelligence; Computer Science, Cybernetics

    Abstract

    This paper describes a two-phase approach for automating the agent-building process when the agent is to perform tactical tasks. The research is inspired by how humans learn-first by observation of a teacher's performance and then by practicing the performance themselves. The objectives of this approach are to produce a high-performing agent that 1) approaches or exceeds the proficiency of a human and 2) does so in a human-like manner. We accomplish these objectives by combining observational learning with experiential learning. These processes are executed sequentially, with the former creating a competent but somewhat limited human-like model from scratch, and the latter improving its performance without significantly eroding its human-like qualities. The process is described in detail, and test results confirming our hypothesis are described.

    Journal Title

    Ieee Transactions on Systems Man and Cybernetics Part B-Cybernetics

    Volume

    41

    Issue/Number

    3

    Publication Date

    1-1-2011

    Document Type

    Article

    Language

    English

    First Page

    792

    Last Page

    804

    WOS Identifier

    WOS:000290734400016

    ISSN

    1083-4419

    Share

    COinS