Dear Colleagues,
We are pleased to announce an exciting opportunity for a postdoctoral researcher to join our team in CIRRELT, Montreal. We are seeking a highly motivated and talented individual to contribute to our ongoing research in the application of reinforcement learning methods in the context of solving stochastic network optimization models. The specifics of the current position are detailed below.
We encourage applications from individuals with a strong background in reinforcement learning and a good understanding of optimization methodologies. Our team is committed to creating an inclusive environment that promotes the advancement of underrepresented groups in academia.
We would appreciate it if you could forward this announcement to any potential candidates that you might know. Best regards,
Walter Rei, Teodor Gabriel Crainic, Fatemeh Sarayloo
Postdoctoral Research Position at CIRRELT, Montreal, Canada: Integrating Reinforcement Learning and Stochastic Network Design
The University of Quebec at Montreal (School of Management) (ESG UQAM) and CIRRELT invite applications for a postdoctoral position focusing on Integrating Reinforcement Learning and Stochastic Network Design.
The successful candidate will join a vibrant research team at CIRRELT and work on cutting-edge projects at the intersection of Reinforcement Learning and Optimization. The candidate will also have the opportunity to receive
training as a visiting scholar at the University of Illinois Chicago as part of the postdoc training program.
.
Research Summary
This research aims to explore the integration of reinforcement learning (RL) algorithms, with a particular focus on deep learning, and optimization methods to address stochastic network design problems. The goal is to enhance the
synergy between reinforcement learning and optimization methods to effectively explore extensive solution spaces. The anticipated outcomes promise to significantly influence the field by offering more robust and efficient solution
methods for complex, large-scale optimization problems in uncertain environments. The project will progress through three stages, designed to understand, utilize, and integrate RL and optimization techniques for stochastic network design.
The projected methodological advancements will encompass theoretical analysis, algorithm development, and empirical analysis, featuring the creation of customized RL frameworks specifically designed for the problems studied.
Position Overview
Supervisor: Walter Rei
Co-Supervisors: Teodor Gabriel Crainic and Fatemeh Sarayloo
Location: CIRRELT, Montreal
Start Time: ASAP
Duration: 1 year (with the possibility of extensions)
Application Deadline: Until the position is filled.
Responsibilities
Conduct innovative research in applying RL techniques to solve stochastic combinatorial optimization problems. Develop novel RL algorithms and frameworks tailored to specific optimization challenges.
Collaborate with interdisciplinary teams and contribute to ongoing projects. Publish research findings in top-tier conferences and journals.
Qualifications
Ph.D. in Computer Science, Operations research, Mathematics, or related fields. Strong background in reinforcement learning, a good understanding of optimization problems, etc. Proficiency in programming languages
(Python, Cplex, TensorFlow, PyTorch, etc.). Excellent research track record demonstrated through publications.
Preferred Skills: Experience in applying RL to optimization problems.
Knowledge of Markov Decision Processes and Deep Reinforcement Learning.
Ability to work independently and collaborate effectively within a team.
Benefits
The position offers a competitive salary package commensurate with experience and qualifications. Access to state-of-the-art resources and a collaborative research environment.
Attending conferences and presenting the research findings. Opportunities for career development and networking.
Application Instructions
Interested candidates should submit the following documents: 1) Curriculum Vitae, 2) Cover Letter detailing research interests and goals, 3) A sample of scientific publications produced (1 or 2)
4) Contact information for three references.
Applications will be reviewed on a rolling basis until the position is filled.
Contact Information
For inquiries or to submit applications, please contact
Teodor Gabriel Crainic
Walter Rei ([email protected]), and
Fatemeh Sarayloo ([email protected]).