CMOS and beyond CMOS
Discover why imec is the premier R&D center for advanced logic & memory devices. anced logic & memory devices.
Connected health solutions
Explore the technologies that will power tomorrow’s wearable, implantable, ingestible and non-contact devices.
Life sciences
See how imec brings the power of chip technology to the world of healthcare.
Sensor solutions for IoT
Dive into innovative solutions for sensor networks, high speed networks and sensor technologies.
Artificial intelligence
Explore the possibilities and technologies of AI.
More expertises
Discover all our expertises.
Be the first to reap the benefits of imec’s research by joining one of our programs or starting an exclusive bilateral collaboration.
Build on our expertise for the design, prototyping and low-volume manufacturing of your innovative nanotech components and products.
Use one of imec’s mature technologies for groundbreaking applications across a multitude of industries such as healthcare, agriculture and Industry 4.0.
Venturing and startups
Kick-start your business. Launch or expand your tech company by drawing on the funds and knowhow of imec’s ecosystem of tailored venturing support.
/Job opportunities/Limited Precision Reinforcement Learning

Limited Precision Reinforcement Learning

PhD - Leuven | About a week ago

Design deep reinforcement learning algorithms that can operate on low precision hardware

Reinforcement learning (RL) is a key AI paradigm for the development of truly autonomous systems. It allows learning controllers to determine optimal policies from trial-and error interactions with the controlled system. Over the last few years, reinforcement learning, in combination with deep neural networks, has been shown to be an extremely powerful learning method This was demonstrated by the well-publicized victory of the AlphaGo program over human champion Go players, an AI feat which was thought to still be years away. Other success stories have seen deep reinforcement learning algorithms reach human level performance in the StarCraft computer game, learn control of complex robotic systems and automate climate control of data centers. 

While current results are impressive, the deployment of reinforcement learning on autonomous systems like mobile robots still faces major hurdles. State-of-art RL controllers rely on massive amounts compute power for both training and online decision making.  This computational demand comes at a large environmental and economic cost.  Moreover, relying on large, distributed compute systems prohibits the deployment of reinforcement learning in autonomous systems that have limited amounts of both compute and energy. One possible solution is to rely on custom machine learning accelerators that offer more efficient computation. Novel compute paradigms, such as compute-in-memory approaches, promise to improve energy efficiency by orders of magnitudes, while still allowing for high throughput. Running RL on these accelerators, however, will require changes at an algorithmic level. 

The focus of this PhD will be the development of deep reinforcement learning algorithms for limited precision hardware. Initially, research will focus on the deployment of trained control policies in limited precision settings. This will require running the policies using low bit-width calculations and training them to be robust to the possible errors this loss of precision introduces. In later stages, research will move to model-based RL approaches that use predictive models to directly compute optimal policies on the low-precision hardware. Other opportunities that can be explored are, among others, the use of graph neural networks, hierarchical reinforcement learning, or meta reinforcement learning. These techniques have shown great potential in grasping relations in the environment, better generalization, and faster task learning. These elements can strongly benefit performance of reinforcement learning algorithms in a context with limited precision hardware. 


The PhD research will take place at Imec Leuven in collaboration with IDLab Antwerp.  

Imec is a world-leading research and innovation hub in nanoelectronics and digital technologies. The machine learning program at Imec is leading the quest for computationally- and energy-efficient machine learning accelerators.  By leveraging its memory technology, Imec aims to develop analog compute-in-memory (ACiM) solutions built on emerging non-volatile memory devices. These devices can mitigate the challenges related to learning algorithms, by performing the computations in the memory itself. Compared to classical Von Neumann architectures, in which computations are performed on a central processor after memory elements have been fetched from outside, compute-in-memory approaches have the promise to increase energy efficiency by orders of magnitudes, while at the same time allowing for the required high throughput. Imec‘s machine learning research is driving the co-evolution of hardware and algorithms needed to facilitate the move to this new computational paradigm 


IDLab Antwerp is a core research group of imec that has initiated different AI research lines over the past years, building on experience from its first, highly successful AI projects including a prize in a DARPA challenge on spectrum management. These research lines include, among others, work on reinforcement learning, embodied AI, and resource-aware AI. Within the Flanders AI research program, IDLab Antwerp is involved in the second challenge focusing on edge and tiny AI, while also leading the 4th challenge on Human-like AI. 



Required background: Computer Science, Machine Learning

Type of work: 40% algorithm design, 40% experimental, 20% literature

Supervisor: Steven Latré

Daily advisor: Peter Vrancx

The reference code for this position is 2021-066. Mention this reference code on your application form.

This website uses cookies for analytics purposes only without any commercial intent. Find out more here. Our privacy statement can be found here. Some content (videos, iframes, forms,...) on this website will only appear when you have accepted the cookies.