Reinforcement Learning: Sample Efficiency, Generalisation, and AI Applications

Dear Colleagues,

Reinforcement learning (RL) continues to reshape the landscape of artificial intelligence, providing powerful tools for solving complex, sequential decision-making problems across a wide spectrum of domains. From fine-tuning large language models (LLMs) to enabling autonomous systems and managing critical infrastructure, RL has proven its versatility and transformative potential.

This Special Issue seeks to highlight recent advances, novel applications, and underexplored dimensions of RL that are shaping the future of intelligent systems. We particularly welcome contributions that introduce innovations in experience replay, algorithm design, sample efficiency, generalisation, safety, interpretability, and real-world deployment.

We invite researchers and practitioners from diverse disciplines to contribute high-quality work—ranging from theoretical developments and methodological insights to applied research and interdisciplinary case studies. This is a timely opportunity to exchange ideas, inspire new directions, and spotlight impactful use cases of RL.

Topics of Interest include, but are not limited to the following:

• RL for robotics, dexterous manipulation, and swarm intelligence;
• RL in autonomous driving, drone navigation, and transport systems;
• Sample-efficient, generalisable, and robust RL algorithms;
• New paradigms in experience replay and memory architectures;
• RL in control of nuclear plants, water systems, and renewable energy grids;
• RL for training or fine-tuning large language models (LLMs);
• Human-in-the-loop RL and preference-based learning;
• RL for summarisation, dialogue systems, and alignment with human intent;
• RL for environmental forecasting and climate resilience;
• Offline, safe, interpretable, and explainable RL;
• Multi-agent reinforcement learning (MARL) and coordination strategies;
• RL applications in healthcare, finance, logistics, and smart infrastructure;
• Benchmarks, reproducibility, and open-source RL frameworks.

We aim to make this Special Issue both inclusive and impactful, welcoming contributions that expand the boundaries of RL from both the academic and industrial communities. Whether your work addresses foundational challenges or introduces creative applications, we would be delighted to consider your submission.

Please feel free to contact us with any queries or to discuss the suitability of your work.

We look forward to receiving your contribution and showcasing the latest innovations in reinforcement learning.

Best wishes in your research,

Dr. Abdulrahman Altahhan
Prof. Dr. Vasile Palade
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. Electronics 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.

• reinforcement learning
• sample efficiency
• over-estimation
• generalisation
• on-policy
• off-policy
• offline
• online
• policy gradient
• experience replay
• full experience replay
• LLMs
• human-in-the-loop
• robotics
• autonomous driverless cars
• multi-agent RL
• control