Evaluating the impact of curriculum learning on the training process for an intelligent agent in a video game

• Main Authors: Jorge E Camargo, Rigoberto Sáenz
• Format: Article
• Language: English
• Published: Asociación Española para la Inteligencia Artificial 2021-09-01
• Series: Inteligencia Artificial
• Subjects: Curriculum Learning; Game AI; Unity Machine Learning Agents; Training Curriculum; Mean Cumulative Reward; Proximal Policy Optimization
• Online Access: http://journal.iberamia.org/index.php/intartif/article/view/532

We want to measure the impact of the curriculum learning technique on a reinforcement training setup, several experiments were designed with different training curriculums adapted for the video game chosen as a case study. Then all were executed on a selected game simulation platform, using two reinforcement learning algorithms, and using the mean cumulative reward as a performance measure. Results suggest that curriculum learning has a significant impact on the training process, increasing training times in some cases, and decreasing them up to 40% percent in some other cases.