Research Article
Neuroevolution vs Reinforcement Learning for Training Non Player Characters in Games: The Case of a Self Driving Car
7 downloads
@INPROCEEDINGS{10.1007/978-3-030-76426-5_13, author={Kristi\^{a}n Kovalsk\"{y} and George Palamas}, title={Neuroevolution vs Reinforcement Learning for Training Non Player Characters in Games: The Case of a Self Driving Car}, proceedings={Intelligent Technologies for Interactive Entertainment. 12th EAI International Conference, INTETAIN 2020, Virtual Event, December 12-14, 2020, Proceedings}, proceedings_a={INTETAIN}, year={2021}, month={5}, keywords={Neuroevolution Reinforcement learning Neural network Evolutionary algorithm Autonomous systems Self driving car Unity Games Non player character NPC}, doi={10.1007/978-3-030-76426-5_13} }- Kristián Kovalský
George Palamas
Year: 2021
Neuroevolution vs Reinforcement Learning for Training Non Player Characters in Games: The Case of a Self Driving Car
INTETAIN
Springer
DOI: 10.1007/978-3-030-76426-5_13
Abstract
The aim of this project is to compare two popular machine learning methods, a non-gradient-based algorithm such as neuro-evolution with a gradient-based reinforcement learning on an irregular task of training a car to self-drive around 3D circuits with varying complexity. A series of 3D circuits with a physics based car model were modeled using the Unity game engine. The data collected during evaluation show that neuro-evolution converges faster to a solution when compared to the reinforcement learning approach. However, when the reinforcement learning approach is allowed to train for long enough, it outperforms the neuro-evolution in terms of car speed and lap times achieved by the trained model of the car.
Copyright © 2020–2025 ICST
