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

Authors

  • Jorge E Camargo Universidad Nacional de Colombia, Colombia
  • Rigoberto Sáenz Universidad Nacional de Colombia, Colombia

DOI:

https://doi.org/10.4114/intartif.vol24iss68pp1-20

Keywords:

Curriculum Learning, Game AI, Unity Machine Learning Agents, Training Curriculum, Mean Cumulative Reward, Proximal Policy Optimization

Abstract

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.

Downloads

Download data is not yet available.

Downloads

Published

2021-09-30

How to Cite

Camargo, J. E., & Sáenz, R. (2021). Evaluating the impact of curriculum learning on the training process for an intelligent agent in a video game. Inteligencia Artificial, 24(68), 1–20. https://doi.org/10.4114/intartif.vol24iss68pp1-20