An innovative simultaneous stochastic optimization approach is proposed that combines actor-critic reinforcement learning and stochastic mathematical programming techniques to determine infill drilling locations in a mining complex. In strategic mine planning under uncertainty, the long-term production schedule is designed to define the extraction sequence, destination policy, and processing stream that maximize net present value and minimize deviations from production targets. The optimized decisions are driven by the inputs; a set of stochastic orebody simulations that describe the materials in the ground; and the design of the engineering system used to transform extracted materials into valuable products. The following work investigates the value of information by determining if additional infill drilling would lead to changes in the long-term production schedule by adapting the schedule using simultaneous stochastic optimization. Additional data is collected by infill drilling and the samples are used to update the stochastic simulations of the material attributes. A case study at a copper mining complex is completed to test the simultaneous stochastic approach for selecting infill drilling locations and demonstrates a 5.7% increase in net present value given a $1 M budget.