Memory Reduction via Delayed Simulation

We address a central (and classical) issue in the theory of infinite games: the reduction of the memory size that is needed to implement winning strategies in regular infinite games (i.e., controllers that ensure correct behavior against actions of the environment, when the specification is a regular omega-language). We propose an approach which attacks this problem before the construction of a strategy, by first reducing the game graph that is obtained from the specification. For the cases of specifications represented by "request-response"-requirements and general "fairness" conditions, we show that an exponential gain in the size of memory is possible.