Novel Reinforcement Learning Research Platform for Role-Playing Games

Petra Csereoka, Bogdan-Ionuţ Roman, Mihai Victor Micea and Călin-Adrian Popa ()
Additional contact information
Petra Csereoka: Department of Computer and Software Engineering, Polytechnic University Timişoara, Blvd. V. Pârvan, No. 2, 300223 Timişoara, Romania
Bogdan-Ionuţ Roman: Department of Computer and Software Engineering, Polytechnic University Timişoara, Blvd. V. Pârvan, No. 2, 300223 Timişoara, Romania
Mihai Victor Micea: Department of Computer and Software Engineering, Polytechnic University Timişoara, Blvd. V. Pârvan, No. 2, 300223 Timişoara, Romania
Călin-Adrian Popa: Department of Computer and Software Engineering, Polytechnic University Timişoara, Blvd. V. Pârvan, No. 2, 300223 Timişoara, Romania

Mathematics, 2022, vol. 10, issue 22, 1-12

Abstract: The latest achievements in the field of reinforcement learning have encouraged the development of vision-based learning methods that compete with human-provided results obtained on various games and training environments. Convolutional neural networks together with Q-learning-based approaches have managed to solve and outperform human players in environments such as Atari 2600, Doom or StarCraft II, but the niche of 3D realistic games with a high degree of freedom of movement and rich graphics remains unexplored, despite having the highest resemblance to real-world situations. In this paper, we propose a novel testbed to push the limits of deep learning methods, namely an OpenAI Gym-like environment based on Dark Souls III, a notoriously difficult role-playing game, where even human players have reportedly struggled. We explore two types of architectures, Deep Q-Network and Deep Recurrent Q-Network, providing the results of a first incursion into this new problem class. The source code for the training environment and baselines is made available.

Keywords: Deep Q-Network; Deep Recurrent Q-Network; Dark Souls III; video games; visual-based reinforcement learning; neural networks (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/22/4363/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/22/4363/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:22:p:4363-:d:978403

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().