In this paper we present a throttling mechanism for optimistic simulations of multi-agent systems, which delays read accesses to the shared simulation state that are likely to be rolled back. We develop a decision- theoretic model of rollback and show how this can be used to derive the optimal time to delay a read event so as to minimise the expected overall execution time of the simulation. We briefly describe an implementation of this approach in ASSK, a distributed simulation kernel developed to investigate synchronisation mechanisms for MAS simulation, and report the results of preliminary experiments to evaluate the effectiveness of our approach.