A control strategy is employed that modifies the stochastic escape times from one basin of attraction to another in a model of a double-gyre flow. The system studied captures the behavior of a large class of fluid flows that circulate and have multiple almost invariant sets. In the presence of noise, a particle in one gyre may randomly switch to an adjacent gyre due to a rare large fluctuation. We show that large fluctuation theory may be applied for controlling autonomous agents in a stochastic environment, in fact leveraging the stochasticity to the advantage of switching between regions of interest and concluding that patterns may be broken or held over time as the result of noise. We demonstrate that a controller can effectively manipulate the probability of a large fluctuation; this demonstrates the potential of optimal control strategies that work in combination with the endemic stochastic environment. To demonstrate this, stochastic simulations and numerical continuation are employed to tie together experimental findings with predictions.