Using reflective learning to master opponent strategy in a competitive environment

Mark A. Cohen, Frank E. Ritter, Steven R. Haynes

Research output: Contribution to conferencePaperpeer-review

4 Scopus citations

Abstract

Cognitive models of people interacting in competitive environments can be useful, especially in games and simulations. To be successful in such environments, it is necessary to quickly learn the strategy used by the opponent. In addition, as the opponent adjusts its tactics, it is equally important to quickly unlearn opponent strategies that are no longer used. In this paper, we present human performance data from a competitive environment. In addition, a cognitive model that uses reflective learning is introduced and compared to the empirical findings. The model demonstrates that it is possible to simulate learning in an adversarial environment using reflection and provides insight into how such a model can be expanded.

Original languageEnglish (US)
Pages157-162
Number of pages6
StatePublished - 2007
Event8th International Conference on Cognitive Modeling, ICCM 2007 - Ann Arbor, United States
Duration: Jul 26 2007Jul 29 2007

Conference

Conference8th International Conference on Cognitive Modeling, ICCM 2007
CountryUnited States
CityAnn Arbor
Period7/26/077/29/07

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Modeling and Simulation

Fingerprint Dive into the research topics of 'Using reflective learning to master opponent strategy in a competitive environment'. Together they form a unique fingerprint.

Cite this