Call for Papers |
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 of the Algorithms journal 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 Additional information --------- /Algorithms/ (ISSN 1999-4893, CiteScore 3.7, indexed by *MathSciNet*, *Scopus*, *EI Compendex*, and *ESCI*—Web of Science) received the first journal Impact Factor for 2022 of 2.3 from Web of Science. All submissions are peer-reviewed, and accepted papers will be published online shortly. Author benefits: Open Access: — free for readers, with article processing charges (APC) paid by authors or their institutions. High Visibility: indexed within Scopus, ESCI (Web of Science), Ei Compendex, MathSciNet, and other databases. Journal Rank: CiteScore - Q2 (Numerical Analysis) No copyright constraints; rapid publication; no space constraints; no extra space or color charges; low fees. |
Credits and Sources |
[1] ERL 2023 : Algorithms Special Issue - Algorithms in Evolutionary Reinforcement Learning |