Computer system, method and computer network for architectural design layout

Electronic design automation (EDA) of the present invention logically places components of an electronic circuit onto an electronic design space to determine an architectural design layout of the electronic circuit. The EDA evaluates a meta-heuristic algorithm starting from an initial layout of elements of the electronic circuit on the electronic design space to provide a plurality of possible layouts for placing the elements of the electronic circuit onto the electronic design space. The EDA utilizes multiple possible layouts of a meta-heuristic algorithm to train one or more probability functions of a model-based reinforcement learning (RL) algorithm. The EDA evaluates a model-based RL algorithm using one or more probability functions to determine an architectural design layout. The EDA may further iteratively enhance the architectural design layout by reevaluating the meta-heuristic algorithm starting from the architectural design layout as an initial layout of the elements, retraining the one or more prob