algorithms

Editorial
Why Reinforcement Learning?
Mehmet Emin Aydin 1, * , Rafet Durgut 2 and Abdur Rakib 3

1 School of Computer Science and Creative Technologies, University of the West of England,
Bristol BS16 1QY, UK
2 Crystalloids BV, 3013 AK Rotterdam, The Netherlands; durgutrafet@gmail.com
3 Centre for Future Transport and Cities, Coventry University, Coventry CV1 5FB, UK; ad9812@coventry.ac.uk
* Correspondence: mehmet.aydin@uwe.ac.uk

The term Artificial Intelligence (AI) has come to be one of the most frequently ex-
pressed keywords around the globe. Machine learning (ML) continues to gain popularity
in the provision of solutions to both industrial and everyday problems, and advancements
in infrastructure computing technologies have driven a surge of interest in AI, ML, and
particularly large language models (LLMs). This involves huge data stocks and bulky
data processing. However, many real-world problems lack the necessary existing data
for modelling and model training. Furthermore, numerous dynamic problems do not
retain data for later use due to constantly evolving circumstances, resulting in significant
challenges in identifying or uncovering patterns (domain knowledge) within such dynamic
structures and situations. These problems remain as significant and outstanding challenges.
Reinforcement learning is a type of active learning whereby a trainee agent learns by
performing desired tasks. This is very useful, especially when labelled data are unavailable
or difficult to obtain beforehand but can only be accessed while running the system.
Moreover, it is particularly useful for dynamic and non-stable problems, as well as online
and ever-changing cases. Robotic and gaming applications are two well-known areas of
application, and researchers are increasingly focusing on numerous emerging use cases [1].
Reinforcement learning (RL), a modern machine learning paradigm, enables an AI-
driven system (known as an agent) to learn in an interactive environment via trial and error
using feedback from its own actions and experiences [2]. The basic idea behind RL is to
train the agent by a reward-and-punishment mechanism [3] whereby the agent receives
rewards for performing correct actions and is punished for incorrect ones. Through this
process, the agent aims to maximize appropriate choices while minimizing incorrect ones.
This has paved the way for allowing learning agents to adapt to changing circumstances
Citation: Aydin, M.E.; Durgut, R.;
in order to fulfil a specific goal, as, based on the feedback responses, the agent assesses its
Rakib, A. Why Reinforcement
Learning? Algorithms 2024, 17, 269.
performance and responds appropriately [4].
https://doi.org/10.3390/a17060269
The well-known application domains of RL appear to be self-driving cars, robotics for
industrial automation, business strategy planning, trading and finance, aircraft and robot
Received: 22 May 2024 motion control, healthcare, and gaming, among others [1,5,6]. In fact, research on RL has
Accepted: 17 June 2024
expanded in a variety of areas, making it a prominent topic in studies of AI, ML, multi-agent
Published: 20 June 2024
systems, and data science. RL researchers have developed theories, algorithms, and systems
to address real-world problems that require learning through feedback over time.
Although RL is not yet widely used in real-world applications, research on RL has
Copyright: © 2024 by the authors.
shown promising results. In the creation of this Special Issue, we received several submis-
Licensee MDPI, Basel, Switzerland. sions and have successfully accepted five application articles along with one review article,
This article is an open access article which can be seen in the list of contributions below. The application articles—listed as
distributed under the terms and contributions 1, 2, 3, 4 and 5—detail the approaches/methodologies employed to utilise
conditions of the Creative Commons the emerging capabilities of reinforcement learning for targeted application scenarios. Each
Attribution (CC BY) license (https:// application case is very distinct, ranging from economic models to continuous control
creativecommons.org/licenses/by/ problems. Additionally, the review article—contribution 6—elaborates how inverse rein-
4.0/). forcement learning can help design and develop the theory of mind, as it is recognised to

Algorithms 2024, 17, 269. https://doi.org/10.3390/a17060269 https://www.mdpi.com/journal/algorithms

help identify the preferences of decision makers from their behaviours, thereby unveiling
the cognitive maps of decision makers.
We would like to extend our heartfelt gratitude to the anonymous reviewers for
their invaluable contributions to the review process in this Special Issue. Your excellent
evaluations, constructive feedback, and unwavering commitment to academic excellence
have significantly enhanced the quality and rigor of the published works.

Conflicts of Interest: The authors declare that they have no conflict of interest.

List of Contributions
1. Souza, G.K.B.; Santos, S.O.S.; Ottoni, A.L.C.; Oliveira, M.S.; Oliveira, D.C.R.; Nepomu-
ceno, E.G. Transfer Reinforcement Learning for Combinatorial Optimization Problems.
Algorithms 2024, 17, 87. https://doi.org/10.3390/a17020087.
2. Gao, D.; Wang, S.; Yang, Y.; Zhang, H.; Chen, H.; Mei, X.; Chen, S.; Qiu, J. An Intelligent
Control Method for Servo Motor Based on Reinforcement Learning. Algorithms 2024,
17, 14. https://doi.org/10.3390/a17010014.
3. Clarke, R.; Fletcher, L.; East, S.; Richardson, T. Reinforcement Learning Derived
High-Alpha Aerobatic Manoeuvres for Fixed Wing Operation in Confined Spaces.
Algorithms 2023, 16, 384. https://doi.org/10.3390/a16080384.
4. Engelhardt, R.C.; Oedingen, M.; Lange, M.; Wiskott, L.; Konen, W. Iterative Oblique
Decision Trees Deliver Explainable RL Models. Algorithms 2023, 16, 282. https://doi.
org/10.3390/a16060282.
5. Deák, S.; Levine, P.; Pearlman, J.; Yang, B. Reinforcement Learning in a New Keynesian
Model. Algorithms 2023, 16, 280. https://doi.org/10.3390/a16060280.
6. Ruiz-Serra, J.; Harré, M.S. Inverse Reinforcement Learning as the Algorithmic Basis
for Theory of Mind: Current Methods and Open Problems. Algorithms 2023, 16, 68.
https://doi.org/10.3390/a16020068.

References
1. Gronauer, S.; Diepold, K. Multi-agent deep reinforcement learning: A survey. Artif. Intell. Rev. 2022, 55, 895–943. [CrossRef]
2. Sutton, R.S.; Barto, A.G. Reinforcement Learning: An Introduction; MIT Press: Cambridge, MA, USA, 2018.
3. Kaelbling, L.P.; Littman, M.L.; Moore, A.W. Reinforcement Learning: A Survey. J. Artif. Intell. Res. 1996, 4, 237–285. [CrossRef]
4. Shakya, A.K.; Pillai, G.; Chakrabarty, S. Reinforcement learning algorithms: A brief survey. Expert Syst. Appl. 2023, 231, 120495.
[CrossRef]
5. Milani, S.; Topin, N.; Veloso, M.; Fang, F. Explainable Reinforcement Learning: A Survey and Comparative Review. ACM Comput.
Surv. 2024, 56, 1–36. [CrossRef]
6. Song, Y.; Suganthan, P.N.; Pedrycz, W.; Ou, J.; He, Y.; Chen, Y.; Wu, Y. Ensemble reinforcement learning: A survey. Appl. Soft
Comput. 2023, 149, 110975. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.