Treatment planning is the gateway connecting various pretreatment and therapeutic information and is critical in determining the success of radiation therapy. Treatment planning aims to combine various relevant clinical domain knowledge and patient-specific information to provide the best possible dose distribution that delivers a maximum tumoricidal dose to the tumor target while minimizing the normal tissue toxicity. Inverse planning is a widely used approach to derive a patient-specific treatment plan by iteratively optimizing an intricate objective function, whose role is to mathematically rank candidate solutions. This approach has successfully led to clinical implementation of intensity modulated radiation therapy (IMRT) and Volumetric-modulated arc therapy (VMAT) 1–6 and the development of several other promising modalities such as station parameter optimized radiation therapy (SPORT). However, the planning process, routinely used in the clinical practice, is rather tedious and labor intensive, yet has no guarantees of generating truly optimal treatment plans. 7 This mainly emanates from the involvement of several model tuning parameters (e.g., the weighting importance factors and target prescription in the objective function) in treatment planning. 7–10 In general, these parameters are manually tuned on a trial-and-error and population-average basis because their influence on the final dose distribution is not known until performing the optimization. As a result, treatment planning remains one of the most labor-intensive and time-consuming tasks in current radiation therapy practice.