Background and Motivation Industrial systems account for 54% of global energy usage [6] and 24% of global net anthropogenic Greenhouse Gas (GHG) emissions. The latter percentage rises to 34% if indirect emissions from energy are included, which would make industrial systems the highest emitting sector [35]. Due to increasing global demand for the products and services enabled by industrial systems, emissions from this sector will continue to rise [26]. However, there is strong evidence that interventions such as reduction in energy use per unit of output [38], lightweight designs and extended product lifetimes can facilitate critical emissions reductions across industrial systems [21]. Yet, optimizing industrial systems is not straightforward; subsectors such as metals, chemicals, waste and cement require customized approaches accounting for different materials, processes and facility configurations. Recent work has shown that reinforcement learning can be leveraged to efficiently control and optimize industrial processes (e.g.