GAIA: A CAD-Like Environment for Designing Game-Playing Agents
Authors:
- 25 May 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 32 (3) , 60-67
Abstract
CAD environments enable designers to construct, evaluate, and revise models of engineering systems. GAIA is a CAD-like environment for designing game-playing agents. Unlike engineering systems, intelligent agents may learn from experience. Thus, in GAIA, the human designer and the intelligent agent cooperate to redesign the agent. In this article, the authors describe three elements of this vision: the interactive environment GAIA, an agent modeling language called TMKL2, and a GAIA module called REM that performs meta-reasoning for self-adaptation in game-playing agents. They illustrate these concepts for designing software agents that play variants of Freeciv, a turn-based strategy game.Keywords
This publication has 12 references indexed in Scilit:
- Interactive Meta-Reasoning: Towards a CAD-Like Environment for Designing Game-Playing Agents2014
- Metareasoning for Self-Adaptation in Intelligent Agents2011
- Design Thinking2011
- Computational Creativity: Coming of AgeAI Magazine, 2009
- Meta-case-based reasoning: self-improvement through self-understandingJournal of Experimental & Theoretical Artificial Intelligence, 2008
- Metacognition in computation: A selected research reviewArtificial Intelligence, 2005
- Introspective reasoning for index refinement in case-based reasoningJournal of Experimental & Theoretical Artificial Intelligence, 2001
- Evaluating PSMs in evolutionary design: the A UTOGNOSTIC experimentsInternational Journal of Human-Computer Studies, 1999
- Fast planning through planning graph analysisArtificial Intelligence, 1997
- Dilemmas in a general theory of planningPolicy Sciences, 1973