학술논문

On Two Mechanisms Associated To Learning: A Mathematical Point Of View
Document Type
Conference
Source
2006 IEEE International Conference on Evolutionary Computation Evolutionary Computation, 2006. CEC 2006. IEEE Congress on. :2262-2269 2006
Subject
Computing and Processing
Organisms
Algorithm design and analysis
Animals
Learning
Power generation economics
Environmental economics
Game theory
State-space methods
Markov processes
Humans
Language
ISSN
1089-778X
1941-0026
Abstract
We study two important features of the mechanisms living organisms seem to use to solve recurrent problems when able to choose strategies from a known set. The first one is forgetting and its influence on the ability of the organism to learn the chance of success of the known strategies. The other feature is selection of strategies according to their relative strengths. Specifically, we compare exponential and hyperbolic forgetting models, and we prove that when the agent has only one strategy available, the estimates for the strategy success rate using the exponential model never converge (in probabilistic terms), whereas the ones using the hyperbolic model converge almost surely. When more strategies are available and proportional selection is used, we prove several results that generalize the one strategy case.