PhD Student in Reinforcement Learning for Control of Partially Observable Dynamical Systems at Linkoping University

  

PhD at Linkoping University


Ref IFM-2023-02171

We have the power of over 40,000 students and co-workers. Students who provide hope for the future. Co-workers who contribute to Linköping University meeting the challenges of the day. Our fundamental values rest on credibility, trust and security. By having the courage to think freely and innovate, our actions together, large and small, contribute to a better world. We look forward to receiving your application!

We are looking for a PhD student in automatic control with specialization within reinforcement learning for control of partially observable dynamical systems.

PhD Project

Linköping University is conducting research in control-related areas such as sensor fusion, learning methods, and optimization. We are seeking a PhD student to focus on the intersection of reinforcement learning and control theory.

Project Summary: Reinforcement Learning (RL) offers a comprehensive framework for controlling dynamic systems, from sensory input to control output. RL has demonstrated remarkable performance, surpassing human champions in strategic games. This project aims to explore, analyze, and develop RL algorithms for controlling partially observable dynamic systems. The research will focus on the following directions:

  • Investigating and quantifying the impact of partial observability, noise, and uncertainty.
  • Exploring efficient utilization of data in RL algorithms, including model-free and model-building approaches.
  • Developing effective algorithms specifically tailored for partially observable dynamic systems.
  • The objective is to combine control theory with recent advancements in RL to create algorithms that efficiently utilize sensor data. The potential use of Kalman filters and model-free observers will also be explored.
This position is part of the Zenith project titled "Reinforcement Learning for partially observable dynamical systems with continuous state and action spaces". For further details about the project, please refer to the provided link.

As a PhD student, the majority of your time will be dedicated to doctoral studies and the research projects you are involved in. There may also be opportunities for teaching or other departmental responsibilities, which will not exceed 20% of a full-time workload.

PhD Qualification

You have graduated at Master’s level in electrical engineering, computer science, engineering physics, applied mathematics or similar, or completed courses with a minimum of 240 credits, at least 60 of which must be in advanced courses within the same topics. Alternatively, you have gained essentially corresponding knowledge in another way.

We are looking for an enthusiastic and ambitious candidate with the following qualifications:

  • Solid background in control theory
  • Knowledge of reinforcement learning
  • Solid programming skills
  • Great communication skills and proficiency in English

PhD Benefits

The salary of PhD students is determined according to a locally negotiated salary progression.

More information about employment benefits at Linköping University is available here.

How to Apply

Apply for the position by clicking the “Apply” button below. Your application must reach Linköping University no later than 11 June 2023.

Applications and documents received after the date above will not be considered.

We welcome applicants with different backgrounds, experiences and perspectives - diversity enriches our work and helps us grow. Preserving everybody's equal value, rights and opportunities is a natural part of who we are. Read more about our work with: Equal opportunities. We look forward to receiving your application!

Linköping university has framework agreements and wishes to decline direct contacts from staffing- and recruitment companies as well as vendors of job advertisements. For further information related to the PhD, please visit this Scholarship Link.

Post a Comment

Previous Post Next Post