A. Mohtasib

Machine Learning Scientist · Robot Learning

Abdalkarim Mohtasib

Karim, to most people.

I work on deep reinforcement learning for robots: teaching them manipulation skills from a handful of human demonstrations, and from rewards they learn to recognise in camera images instead of rewards written by hand.

Portrait of Abdalkarim Mohtasib
Fig. 1The author, outdoors
01 / About

Robots that learn from what they see

I'm a machine learning scientist at Zebra Technologies, working across deep learning, reinforcement learning and robotics.

I did my PhD in Computer Science at the Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UK. My doctoral research was on deep reinforcement learning for robotic manipulation and grasping. It looked at how to combine human demonstrations with reinforcement learning, and how to learn reward functions from visual observations rather than engineering them for every task.

My route into robotics started with hardware. I studied mechatronics engineering at Palestine Polytechnic University and embedded systems at the University of Essex, and my first paper described a self-balancing two-wheel electric vehicle.

I'm always happy to talk about robot learning, share code from my projects, or explore a collaboration. Get in touch.

Now
Machine Learning Scientist, Zebra Technologies
PhD
Computer Science, University of Lincoln (L-CAS)
Interests
Deep RL · Learning from demonstration · Robotic manipulation
02 / Research

Three threads I keep pulling on

Learning from demonstration

Using a small number of human demonstrations to bootstrap reinforcement learning, so a robot needs far less trial and error to master a manipulation skill.

See [1] [2]

Rewards from pixels

Learning reward signals and task-success classifiers directly from camera images, instead of hand-engineering a reward function for every new task.

See [1] [3] [4]

Sequential manipulation

Scaling policy learning to multi-step tasks, where a robot has to reach several sub-goals in the right order to finish the job.

See [1]
03 / Publications

Papers

  1. 2026
    Journal

    Robot policy learning from demonstrations and visual rewards for sequential manipulation tasks

    A. Mohtasib, H. Cuayáhuitl

    Robotics and Autonomous Systems, vol. 198, 105311

    DOI
  2. 2022
    Conference

    Robot policy learning from demonstration using advantage weighting and early termination

    A. Mohtasib, G. Neumann, H. Cuayáhuitl

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7414–7420

    DOI Code
  3. 2021
    Conference

    A study on dense and sparse (visual) rewards in robot policy learning

    A. Mohtasib, G. Neumann, H. Cuayáhuitl

    Towards Autonomous Robotic Systems (TAROS), Lecture Notes in Computer Science, pp. 3–13

    DOI
  4. 2021
    Conference

    Neural task success classifiers for robotic manipulation from few real demonstrations

    A. Mohtasib, E. Amir Ghalamzan, N. Bellotto, H. Cuayáhuitl

    International Joint Conference on Neural Networks (IJCNN), pp. 1–8

    DOI
  5. 2013
    Conference

    Self-balancing two-wheel electric vehicle (STEVE)

    A. M. Mohtasib, M. H. Shawar

    9th International Symposium on Mechatronics and its Applications (ISMA), pp. 1–8

    DOI

The most up-to-date list, with citation counts, is on Google Scholar.

05 / Background

Experience & education

  1. Now

    Machine Learning Scientist

    Zebra Technologies

  2. Doctorate

    Ph.D. in Computer Science

    University of Lincoln, UK · Lincoln Centre for Autonomous Systems (L-CAS)

  3. 2015

    M.Sc. in Embedded Systems

    University of Essex, Colchester, UK

  4. 2012

    B.Eng. in Mechatronics Engineering

    Palestine Polytechnic University, Hebron, Palestine