Analysis, Combination and Integration of Neuroevolution and Backpropagation Algorithms for Gaming Environment

This paper provides a method of combining Neu-roevolution with Backpropagation to achieve lower training times than Neuroevolution when training agents in a video game environment. The combination of these algorithms is reproduced by an alteration of the step of creating a new generation from the mo...

Full description

Saved in:

Bibliographic Details
Published in:	2023 15th International Conference on Electronics, Computers and Artificial Intelligence (ECAI) pp. 1 - 5
Main Authors:	Darii, Andrei, Moll, Maximilian, Nistor, Marian Sorin, Pickl, Stefan, Novac, Ovidiu Constantin, Novac, Cornelia Mihaela, Gordan, Ioan Mircea, Gordan, Cornelia Emilia
Format:	Conference Proceeding
Language:	English
Published:	IEEE 29-06-2023
Subjects:	Backpropagation Backpropagation algorithms Learning (artificial intelligence) Memory management Neural networks Neuroevolution Reinforcement Learning Training Video games
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This paper provides a method of combining Neu-roevolution with Backpropagation to achieve lower training times than Neuroevolution when training agents in a video game environment. The combination of these algorithms is reproduced by an alteration of the step of creating a new generation from the most capable agents with the creation of a new generation through the Backpropagation method using the preventively saved data of the most capable agent from the environment. Thus, for the new generation, a Neural Network trained with backpropagation is assigned instead of the best-performing Neural Network from the previous generation. As a result, the Neuroevolution with the Backpropagation method shows better performance when increasing the target of the environmental performance of the agent.
DOI:	10.1109/ECAI58194.2023.10193958