Atomic Layer Deposition (ALD) is a commonly employed process for producingconformal nanoscale coatings in the microelectronics and energy materials industries.ALD processes are composed of cycles of sequential self-limiting chemicalreactions followed by purges with an inert gas to produce atomically thin coatings.At the end of each cycle, the Growth Per Cycle (GPC) which corresponds to netmass or thickness change from the previous ALD cycle is determined. OptimizingALD processes for stable and uniform GPC for a new combination of reactantsis challenging as the optimal combination of gas timings, temperature, and gaspartial pressures spans a large multidimensional space and in-situ characterizationis typically performed with a limited number of mass sensors. In this work, we useTargeted Adaptive Design (TAD), a Gaussian Process (GP)-based probabilisticmachine learning framework that aims at efficiently and autonomously locatingcontrol parameters that would yield a desired target within specified tolerance, tooptimize simulated ALD processes.