stochastic game model

The problem of the distributed control of the hexapod animat moving on the basis of stochastic game model is investigated. The formulation of a game problem is executed, the adaptive recurrent method and algorithm of its decision are developed. The computer program model of rhythmic change of states of animat feet for the organisation of its moving is constructed. Influence of parameters of model on a control efficiency of animat movement is investigated.

The game model of multi-agent systems of self-organizing in the conditions of uncertainty is developed. The formulation of a stochastic game problem is carried out, criteria of self-organizing of strategies of players are defined, a recurrent method, algorithm and software of learning of multi-agent system to simulate the synchronised rhythmic luminescence of a colony of fireflies are developed.

The stochastic game model of the data clustering under the influence of noise is offered. Adaptive recurrent method and algorithm of stochastic game solving are developed. Computer modeling of game of noisy data clustering is executed. The parameter influences on convergence of stochastic game method of the data clustering are studied. The analysis of received results is realized.