Reinforcement Learning and Gamification: a Framework for Integrating Intelligent Agents In Retro Video Games

Nemanja Josipovic; Aleksandar Petrovic; Aleksa Cuk; Milos Antonijevic; Dejan Jovanovic; Nebojsa Budimirovic

doi:10.2991/978-94-6463-482-2_7

<Previous Article In Volume

Next Article In Volume>

Reinforcement Learning and Gamification: a Framework for Integrating Intelligent Agents In Retro Video Games

Authors

Nemanja Josipovic¹, Aleksandar Petrovic¹, Aleksa Cuk¹, Milos Antonijevic¹^{, *}, Dejan Jovanovic²^{, 3}, Nebojsa Budimirovic¹

¹Singidunum University, Faculty of Informatics and Computing, Danijelova 32, 11000, Belgrade, Serbia

²College of Academic Studies “Dositej”, Vojvode Putnika 7, 11000, Belgrade, Serbia

³Singidunum University, Belgrade, Serbia

^*Corresponding author. Email: mantonijevic@singdinum.ac.rs Email: office@singidunum.ac.rs

Corresponding Author

Milos Antonijevic

Available Online 23 August 2024.

DOI: 10.2991/978-94-6463-482-2_7 How to use a DOI?
Keywords: genetic algorithm; artificial intelligence; python; gaming; simulation; reinforcement learning
Abstract: This work explores the benefits that reinforcement learning (RL) and unsupervised learning (UL) have over supervised learning (SL). Using RL and Python simulations are produced that closely mimic those observed in the real world, and an agent is trained using a form of genetic algorithm. The system created can be used to simulate real-world scenarios and offer solutions. Simulations were performed upon a clone of the game “Pong”. The system successfully adapted to the game the more it played, and improved its capability to successfully get high-scoring results. The system is flexible and dynamic, being able to adapt to different simulation environments. In the future, more complex examples will be tested on the system, with the goal of real-world scenario simulation.
Copyright: © 2024 The Author(s)
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 2nd International Conference on Innovation in Information Technology and Business (ICIITB 2024)
Series: Advances in Computer Science Research
Publication Date: 23 August 2024
ISBN: 978-94-6463-482-2
ISSN: 2352-538X
DOI: 10.2991/978-94-6463-482-2_7 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Nemanja Josipovic
AU  - Aleksandar Petrovic
AU  - Aleksa Cuk
AU  - Milos Antonijevic
AU  - Dejan Jovanovic
AU  - Nebojsa Budimirovic
PY  - 2024
DA  - 2024/08/23
TI  - Reinforcement Learning and Gamification: a Framework for Integrating Intelligent Agents In Retro Video Games
BT  - Proceedings of the 2nd International Conference on Innovation in Information Technology and Business (ICIITB 2024)
PB  - Atlantis Press
SP  - 87
EP  - 101
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-482-2_7
DO  - 10.2991/978-94-6463-482-2_7
ID  - Josipovic2024
ER  -

download .riscopy to clipboard