Evaluating the impact of curriculum learning on the training process for an intelligent agent in a video game
Open Access
- 30 September 2021
- journal article
- research article
- Published by IBERAMIA: Sociedad Iberoamericana de Inteligencia Artificial in INTELIGENCIA ARTIFICIAL
- Vol. 24 (68), 1-20
- https://doi.org/10.4114/intartif.vol24iss68pp1-20
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.Keywords
This publication has 3 references indexed in Scilit:
- Deep Learning for Video Game PlayingIEEE Transactions on Games, 2019
- Deep Reinforcement Learning: A Brief SurveyIEEE Signal Processing Magazine, 2017
- Universal Intelligence: A Definition of Machine IntelligenceMinds and Machines, 2007