Dear Colleagues, 

Recent years have witnessed a surge in the number of novel approaches to reinforcement learning (RL) based on evolutionary computation, forming the exciting research area of evolutionary RL. Due to their comparative advantages, including better exploration properties, such approaches are particularly promising in the context of RL tasks with sparse or deceptive rewards, ill-defined problems (e.g., design), and problems that require the generation of a large number of diverse solutions. Quality diversity approaches, such as MAP-Elites, provide a striking example. Further research is anticipated the bring the fields of RL and evolutionary computation even closer together, through both hybridisation and the transfer of ideas across the two fields. However, many issues remain, especially related to sample (in)efficiency, lack of consideration of the sequential structure of the underlying problem (as opposed to standard methods), evaluation of noisy functions, and scalability. 

This Special Issue presents an opportunity for researchers to showcase their novel research in the area of evolutionary reinforcement learning. Potential areas of focus include (but are not limited to):

• Dynamic (non-stationary) and/or noisy environments;
• Neuroevolution;
• Divergent search and open-endedness;
• Sample efficiency and few-shot learning;
• Hybrid methods;
• Landscape analysis/metrics;
• Bayesian techniques;
• Scalability;
• Inclusion of additional biological mechanisms.

Submissions are encouraged for new evolutionary RL algorithms, enhancements in existing techniques, applications in diverse domains, and survey papers.

Dr. Marko Đurasević
Dr. Bruno Gašperov
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. Algorithms is an international peer-reviewed open access monthly 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 1600 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.

• evolutionary reinforcement learning
• optimal stochastic control
• illumination algorithms
• decision making
• gradient-free reinforcement learning
• hybrid algorithms