Back to Search Start Over

Performance Analysis of Reinforcement Learning Techniques for Augmented Experience Training Using Generative Adversarial Networks

Authors :
Smita Mahajan
Shruti Patil
Moinuddin Bhavnagri
Rashmi Singh
Kshitiz Kalra
Bhumika Saini
Ketan Kotecha
Jatinderkumar Saini
Source :
Applied Sciences, Vol 12, Iss 24, p 12923 (2022)
Publication Year :
2022
Publisher :
MDPI AG, 2022.

Abstract

This paper aims at analyzing the performance of reinforcement learning (RL) agents when trained in environments created by a generative adversarial network (GAN). This is a first step towards the greater goal of developing fast-learning and robust RL agents by leveraging the power of GANs for environment generation. The RL techniques that we tested were exact Q-learning, approximate Q-learning, approximate SARSA and a heuristic agent. The task for the agents was to learn how to play the game Super Mario Bros (SMB). This analysis will be helpful in suggesting which RL techniques are best suited for augmented experience training (with synthetic environments). This would further help in establishing a reinforcement learning framework using the agents that can learn faster by bringing a greater variety in environment exploration.

Details

Language :
English
ISSN :
20763417
Volume :
12
Issue :
24
Database :
Directory of Open Access Journals
Journal :
Applied Sciences
Publication Type :
Academic Journal
Accession number :
edsdoj.403506505f48406db1f70c7e91a660a3
Document Type :
article
Full Text :
https://doi.org/10.3390/app122412923