PhD Student in Reinforcement Learning for Control of Partially Observable Dynamical Systems
Back to available jobsThe control-oriented research at Linköping University concerns different topics such as sensor fusion, learning methods for control, and optimization. We are currently looking for a PhD student to conduct research on the intersection of reinforcement learning and control theory.
Your work assignments
Reinforcement Learning (RL) provides an end-to-end framework to control dynamical systems, from sensory data to control input, and has shown astonishing performance for example in playing strategic games and surpassed human champion performance. This project aims to study, analyze, and develop RL algorithms for control of partially observable dynamical systems. More specifically, the following research directions will be followed:
- To study and quantify the effect of partial observability, noise, and uncertainty
- To study how data can be efficiently used in RL algorithms including model-free and model-building approaches
- To develop efficient algorithms for partially observable dynamical systems
The idea is to leverage control theory and new advances in RL to develop algorithms to use sensor data efficiently. The possibility of using Kalman filters and model-free observers will be investigated.
This position is a part of a Zenith project called "Reinforcement Learning for partially observable dynamical systems with continuous state and action spaces”. For more information about the project, read https://liu.se/en/research/reinforcement-learning-for-partially-observable-dynamical-systems.
As a PhD student, you devote most of your time to doctoral studies and the research projects of which you are part. Your work may also include teaching or other departmental duties, up to a maximum of 20 per cent of full-time.
Your qualifications
You have graduated at Master’s level electrical engineering, computer science, engineering physics, or 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. The degree requirement must be met no later than at the time the employment decision is finalized, which occurs when the employment contract is signed.
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
It is meriting to have knowledge in machine learning, optimization, and statistics. Knowledge of programming with Python is also an advantage.
Your workplace
The Division of Automatic Control is successfully conducting research as well as postgraduate and undergraduate education within areas such as autonomous systems, complex networks, data-driven modeling, learning control, optimization, and sensor fusion. The division has extensive collaborations both with industry and other research groups around the world. Read more about the division here: https://liu.se/en/organisation/liu/isy/rt.
For more information about ISY, go to: https://liu.se/en/article/open-positions-at-isy
The employment
When taking up the post, you will be admitted to the program for doctoral studies. More information about the doctoral studies at each faculty is available at Doctoral studies at Linköping University
The employment has a duration of normally four years’ full-time equivalent. Extension of employment up to five years is based on the degree of teaching and institutional assignment. Further extensions may be granted in exceptional circumstances. You will initially be employed for one year, after which your employment will be renewed for a maximum of two years at a time, depending on your progress through the study plan.
For any questions regarding PhD student responsibilities and processes at ISY, please contact isyphdcouncil@groups.liu.se.
As an employee of Linköping University, you will be eligible for Swedish social benefits. This includes:
- Preventive health care: a tax-free amount of a maximum value of SEK 2,500 per calendar year (can be used for example for training)
- Paid leave: including parental leave and leave for visits to doctors
- Retirement: the national public pension paid by the Swedish Pensions Agency, and from LiU and any previous employers.
Starting date by agreement.
Background screening may come to be carried out before any decision on employment is made.
Salary and employment 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.
Union representatives
Information about union representatives, see Help for applicants.
Application procedure
Apply for the position by clicking the “Apply” button below. Your application must reach Linköping University no later than September 5, 2025.
Applications and documents received after the date above will not be considered.
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.