applsci-logo

Journal Browser

Journal Browser

Advancements and Applications in Reinforcement Learning

A special issue of Applied Sciences (ISSN 2076-3417).

Deadline for manuscript submissions: 30 July 2025 | Viewed by 2025

Special Issue Editors


E-Mail Website
Guest Editor
Athena—Research and Innovation Center in Information, Communication and Knowledge Technologies, Xanthi, Greece
Interests: collective artificial intelligence; multi-agent systems; reinforcement learning agents; extended reality technologies

E-Mail Website
Guest Editor
School of Science and Technology, Hellenic Open University, Patra, Greece
Interests: artificial intelligence; machine learning and e-learning technologies
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Reinforcement learning (RL) is rapidly transforming numerous industries and domains with real-world applications through its capacity to model and adapt learning based on interactions with the environment. This Special Issue (SI) aims to delve into the practical applications and advancements of RL, showcasing how these cutting-edge technologies are driving innovation and efficiency across various sectors.

This SI covers a wide range of topics, including, but not limited to, the following:

  • RL in Robotics and Automation: Exploring how RL is enhancing robotic systems and automation processes.
  • Game Playing and Simulations: Investigating the role of RL in developing sophisticated game-playing agents and realistic simulations.
  • Recommendation Systems: Demonstrating the use of RL for creating personalized recommendation systems.
  • Healthcare and Medicine: Highlighting RL applications in improving healthcare delivery and medical decision making.
  • Multi-Agent Reinforcement Learning: Discussing collaborative systems and the coordination of multiple agents using RL.
  • Autonomous Vehicles and Transportation: Examining how RL is advancing the development of self-driving cars and optimizing transportation systems.
  • Adaptive Control and Scheduling: Presenting RL approaches for dynamic control systems and efficient scheduling.
  • Adaptive User Interfaces and Human–Computer Interactions: Showcasing RL in the design of responsive user interfaces and enhancing user experiences.
  • Crowd Simulation and Management: Investigating the use of RL to model and simulate crowd behaviors, enhancing safety and efficiency in public spaces and events.
  • Realistic Behaviors Modeling: Exploring how RL can be employed to generate realistic human-like behaviors through virtual agents.

We invite submissions that present novel RL algorithms, theoretical advancements, case studies, experimental evaluations, and comprehensive reviews summarizing recent developments. Contributions can range from original research papers to surveys and tutorials, aiming to foster a thorough understanding of RL's real-world impact and potential across various domains.

This Special Issue will serve as a platform to highlight high-quality, original research and innovative ideas, encouraging the exchange of knowledge and the advancement of RL technologies.

Dr. Chairi Kiourt
Prof. Dr. Dimitris Kalles
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • reinforcement learning
  • adaptive control
  • collaborative learning
  • robotics and automation
  • multi-agent systems
  • simulation
  • decision making
  • non-stationary environment.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 2101 KiB  
Article
Policy-Based Reinforcement Learning Approach in Imperfect Information Card Game
by Kamil Chrustowski and Piotr Duch
Appl. Sci. 2025, 15(4), 2121; https://doi.org/10.3390/app15042121 - 17 Feb 2025
Viewed by 643
Abstract
Games provide an excellent testing ground for machine learning and artificial intelligence, offering diverse environments with strategic challenges and complex decision-making scenarios. This study seeks to design a self-learning artificial intelligent agent capable of playing the trick-taking stage of the popular card game [...] Read more.
Games provide an excellent testing ground for machine learning and artificial intelligence, offering diverse environments with strategic challenges and complex decision-making scenarios. This study seeks to design a self-learning artificial intelligent agent capable of playing the trick-taking stage of the popular card game Thousand, known for its complex bidding system and dynamic gameplay. Due to the game’s vast state space and strategic complexity, other artificial intelligence approaches, such as Monte Carlo Tree Search and Deep Counterfactual Regret Minimisation, are infeasible. To address these challenges, the enhanced version of the REINFORCE policy gradient algorithm is proposed. Introducing a score-related parameter β designed to guide the learning process by prioritising valuable games, the proposed approach enhances policy updates and improves overall learning outcomes. Moreover, leveraging the off-policy experience replay, along with the importance weighting of behavioural policy, enhanced training stability and reduced model variance. The proposed algorithm was applied to the trick-taking stage of the popular game Thousand Schnapsen in a two-player setup. Four distinct neural network models were explored to evaluate the performance of the proposed approach. A custom test suite of selected deals and tournament evaluations was employed to assess effectiveness. Comparisons were made against two benchmark strategies: a random strategy agent and an alpha-beta pruning tree search with varying search depths. The proposed algorithm achieved win rates exceeding 65% against the random agent, nearly 60% against alpha-beta pruning at a search depth of 6, and 55% against alpha-beta pruning at the maximum possible depth. Full article
(This article belongs to the Special Issue Advancements and Applications in Reinforcement Learning)
Show Figures

Figure 1

Back to TopTop