Phdjoint Optimization Using Reinforcement Learning

**About the role**: Your role is to carry out a **PHD thesis** about: “**Joint optimization using reinforcement learning for error-correcting encoder and its decoder for mobile transmissions”** **Global context and objective** Channel Coding is an essential component of mobile communication systems. The standardization body 3GPP has launched working groups to define the future 6G standard. The main constraints for channel (de)coding are its flexibility in the data block size to process while increasing the performance compared to the existing (de)coding schemes. Orange is one key player and aims at promoting in 3GPP new enablers, including (de)coding that take into account energy aspects in addition to performance and flexibility. Indeed, channel decoding is the most energy-intensive part of the physical layer. To meet the new 3GPP specifications, the introduction of Artificial Intelligence algorithms to build new error-correcting codes will be an important asset. The use of deep learning techniques (Deep Learning, DL) in the field of radio appears more and more in the technical literature [1, 2]. This technique derived from AI (Artificial Intelligence) allows the overall optimization of radio resources. It can also be applied to improve the quality of the received signal via some optimization in signal processing (demodulation, equalization, decoding of correcting codes, etc.) with limited energy consumption. A third possibility, not still explored, is to use DL to build optimized transmission schemes (for instance joint coding-modulation component) in the fields of performance and energy. The main advantage is that it is an optimization process that has no "real time" constraint, and that can therefore be done initially on computers having enough compute resources (CPUs or GPUs). [1] T. O’Shea and J. Hoydis, "An Introduction to Deep Learning for the Physical Layer," in IEEE Transactions on Cognitive Communications and Networking, vol. 3, no. 4, pp. 563-575, Dec. 2017, doi: 10.1109/TCCN.2017.2758370. [2] H. Kim, S. Oh and P. Viswanath, "Physical Layer Communication via Deep Learning," in IEEE Journal on Selected Areas in Information Theory, vol. 1, no. 1, pp. 5-18, May 2020, doi: 10.1109/JSAIT.2020.2991562 **Scientific objective - results and locks to overcome** [3] A. Elkelesh, M. Ebada, S. Cammerer, L. Schmalen,S. Ten Brink: "Decoder-in-the-Loop: Genetic optimization-based LDPC code design", IEEE Access, vol. 7, 2029, DOI: 10.1109/ACCESS.2019.2942999. [4] L. Huang, H. Zhang, R. Li, Y. Ge, J. Wang: "AI Coding: Learning to construct **About you**: **Skills (scientific and technical) and personal qualities required by the position** - Good knowledge and control in signal processing and digital communications - Knowledge in the field of error correcting codes and Artificial Intelligence - Good knowledge of Python programming tools and C language. - English - Good communication skills **Required training (master, engineering degree, doctorate, scientific and technical field, etc.)** **Desired experiences (internships,)** - One first experience in the field of digital communications **Additional information**: The PHD topic will allow to benefit from an joint expertise in digital communication systems and the use of the Artificial intelligence for solving and improving some Physical layer components. **Department**: L’ambition de la Division Innovation est de porter plus loin l’innovation d’Orange et de renforcer son leadership technologique, en mobilisant nos capacités de recherche pour nourrir une innovation responsable au service de l’humain, éclairer les choix stratégiques du Groupe à long terme et influencer l’écosystème digital mondial. Nous formons les expertes et les experts des technologies d’aujourd’hui et de demain, et veillons à une amélioration continue de la performance de nos services et de notre efficacité. La division Innovation rassemble, dans le monde, 6000 salariés dédiés à la recherche et l’innovation dont 740 chercheurs. Porteurs d’une vision globale avec une grande diversité de profils (chercheurs, ingénieurs, designers, développeurs, data scientists, sociologues, graphistes, marketeurs, experts en cybersécurité ), les femmes et les hommes de Innovation sont à l’écoute et au service des pays, des régions et des business units pour faire d’Orange un opérateur multiservices de confiance. « Au sein de Innovation, vous serez intégré(e) dans une équipe de recherche à la pointe de l’innovation et de l’expertise sur les réseaux du futur (5G+, virtualisation, convergence fixe-mobile, mobile edge computing, Named Data networking, ).Vous ferez partie d’un écosystème de recherche côtoyant des ingénieurs d'études en anticipation (plus court terme) permettant la mise en œuvre concrète des concepts étudiées, bénéficiant de plateformes de simulations (4G/5G) ». **Contract**: Thesis