In the design and operation of nuclear reactors, safety-related goals must be embedded in complex multivariate control strategies. It is often the case that the goals exist only as mental models in the mind of the designer or the operator. In order to effect control that is risk averse, the goals must be translated into an effective control strategy that can be both verified and validated. The relation that these safety goals have to a particular architecture of artificial neural network, the Barto-Sutton architecture, is examined and the capability of the network to embed safety goals in nontrivial control tasks is demonstrated. To realize these goals, the network was extended to encompass a multiple-input/multiple-output control structure.The network synthesizes a control schedule through the construction of artificial precursors to failure; these serve as an additional, virtual layer in the defenses against fission product release. The synthesized schedule can be visually inspected for anomalies and inconsistencies and is validated during training.