Learning Proficient Behavior With Computational Agents in Engineering Configuration Design

Abstract

A novel approach for computational agents to learn proficient behavior in engineering configuration design that is inspired by human learning is introduced in this work. The learning proficient simulated annealing design agents (LPSADA) begin as different proficiency designers and are explicitly modeled to mimic the design behavior and performance of different proficiency human designers. A learning methodology, which is inspired by human learning, is introduced to update the characteristics of the agents that dictate their behavior. The methods are designed to change their behavioral characteristics based on their experience, including a non-deterministic reinforcement learning algorithm. Results show that the lower-proficiency agents successfully change their behavior to act more like high-proficiency designers. These behavior changes are shown to increase the performance of the lower-proficiency agents to the levels of high-proficiency human designers. In sum, the learning methodology that is introduced is shown to allow lower-proficiency agents to become higher-proficiency designers.