Svenja Stark

Research Interests

Machine Learning, Goal-based Learning, Intrinsic Motivation, Reinforcement Learning, Robotics

Contact Information

Mail. Svenja Stark
svenja@robot-learning.de

Svenja Stark joined the Intelligent Autonomous Systems Group as a PhD student in December 2016. She is working on the IKIDA-project, which is about interactive AI algorithms & cognitive models for human-AI interaction.

Previously, she has been working on the GOAL-Robots project that aimed at developing goal-based open-ended autonomous learning robots; building lifelong learning robots.

Before joining the Autonomous Systems Labs, Svenja Stark received a Bachelor and a Master of Science degree in Computer Science from the TU Darmstadt. During her studies, she completed parts of her graduate coursework at the University of Massachusetts in Amherst. Her thesis entitled "Learning Probabilistic Feedforward and Feedback Policies for Generating Stable Walking Behaviors" was written under supervision of Elmar Rueckert and Jan Peters.

Research Interest

multi-task learning, meta-learning, goal-based learning, intrinsic motivation, lifelong learning, Reinforcement Learning, motor skill learning

References

    •     Bib
      Stark, S.; Peters, J.; Rueckert, E. (2019). Experience Reuse with Probabilistic Movement Primitives, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
    •     Bib
      Liu, Z.; Hitzmann, A.; Ikemoto, S.; Stark, S.; Peters, J.; Hosoda, K. (2019). Local Online Motor Babbling: Learning Motor Abundance of a Musculoskeletal Robot Arm, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
    •     Bib
      Delfosse, Q.; Stark, S.; Tanneberg, D.; Santucci, V. G.; Peters, J. (2019). Open-Ended Learning of Grasp Strategies using Intrinsically Motivated Self-Supervision, Workshop at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
    •     Bib
      Stark, S.; Peters, J.; Rueckert, E. (2017). A Comparison of Distance Measures for Learning Nonparametric Motor Skill Libraries, Proceedings of the International Conference on Humanoid Robots (HUMANOIDS).
    •     Bib
      Thiem, S.; Stark, S.; Tanneberg, D.; Peters, J.; Rueckert, E. (2017). Simulation of the underactuated Sake Robotics Gripper in V-REP, Workshop at the International Conference on Humanoid Robots (HUMANOIDS).
    •     Bib
      Stark, S. (2016). Learning Probabilistic Feedforward and Feedback Policies for Generating Stable Walking Behaviors, Master Thesis.

Other Activities