Deep Reinforcement Learning and Its Latest Applications

Dear Colleagues,

Despite a few remarkable achievements, reinforcement learning is a field within artificial intelligence that has seen a relatively limited impact of deep learning techniques thus far. While neural networks have helped overcome some scalability issues associated with traditional methods, the fundamental methodologies have remained largely unchanged, leaving many traditional problems unresolved. There are several challenges that still need to be addressed or better understood in RL: sample efficiency and moving beyond the current “tabula rasa” approach, the exploitation vs. exploration dilemma, the lack of generalization and difficult adaptation to different scenarios, intrinsic vs. extrinsic rewarding systems, and intelligent transfer learning, among many others.

There is a widely held belief that solving the aforementioned challenges, which are interconnected to some extent, requires a significant paradigm shift in the field of RL. This shift is likely to be centered around a more comprehensive and extensive utilization of deep learning techniques. In light of this perspective, we strongly encourage the submission of innovative and visionary works that align with this vision. We welcome contributions that present mature applications addressing tangible problems, as well as well-crafted proof-of-concept articles that showcase and promote pioneering approaches.

Prof. Dr. Andrea Asperti
Guest Editor

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.

• sample efficiency
• multi-agent DRL
• transfer learning
• generalization
• intrinsic rewarding systems
• hierarchical DRL
• sparse reward environments
• multi-objective RL
• partial observability
• multi-task and meta RL