REM (Reflective Evolutionary Mind) is the Cognitive Model, which uses functional models for self-redesign in the context of complex, dynamic environments. Developed by J. William Murdock, a member of Dr. Ashok Goel's Design & Intelligence Laboratory in the School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA. REM project | B. Murdock's Homepage
Email: Этот адрес электронной почты защищён от спам-ботов. У вас должен быть включен JavaScript для просмотра.
Когнитивная модель REM (Reflective Evolutionary Mind) разработана Уильямом Мэрдоком (J. William Murdock) в руководимой Ашоком Гоелем (Ashok Goel) лаборатории (Design & Intelligence Laboratory) Технологического института штата Джорджия (School of Interactive Computing, Georgia Institute of Technology), расположенного в г. Атланта, Джорджия, США.
Общие сведения
REM is an operating environment for intelligent agents. The focus of the REM project is on reflective evolution.
Agents in REM use reasoning about their own processing (i.e., reflection) to make adjustments to this processing (i.e., evolution).
Knowledge and experiences are represented using: Tasks, methods, assertions, traces
Main components: Task-Method-Knowledge (TMK) models provide functional models of what agents know and how they operate. They describe components of a reasoning process in terms of intended effects, incidental effects, and decomposition into lower-level components.
Tasks include the requirements and intended effects of some computation.
Methods implement a task and include a state-transition machine in which transitions are accomplished by subtasks.
Implementation: Common Lisp, using Loom as the underlying knowledge-engine; Java version in development
Funding program, project and environment in which the architecture was applied: NSF Science of Design program; Self Adaptive Agents project; Turn-based strategy games
Main general paradigms: Reflection. Adaptation in response to new functional requirements.
Publications
Selected list of publications
1. Meta-Case-Based Reasoning: Self-Improvement through Self-Understanding. J. William Murdock and Ashok K. Goel. Journal of Experimental & Theoretical Artificial Intelligence, 20(1):1-36, March 2008. (PDF, WWW)
2. Presentations:
- Self-Improvement through Self-Understanding: Model-Based Reflection for Agent Adaptation
Presentation at National Institute of Standards and Technology (NIST), March 18, 2002
(Focuses largely on REM; also discusses SIRRINE)
- Localizing Planning with Functional Process Models
Presentation at ICAPS'03, June 11, 2003 (Adaptation by planning in REM)
- Flexible Reasoning with Functional Models. Presentation at Ohio State University, April 15, 2003
(Discusses REM, SIRRINE, Interactive Kritik, and AHEAD)
- Planning in the Context of Model-Based Adaptation
Presentation for University of Maryland class: CMSC 722 (AI Planning), April 18, 2002
(Describes planning in REM; also refers briefly to SHOP)
