Cansu Sancaktar

I’m a PhD student at the Max Planck Institute for Intelligent Systems, supervised by Prof. Georg Martius. My research focuses on curiosity and intrinsically-motivated Reinforcement Learning (RL).

Taking inspiration from developmental psychology, I’m developing methods to help robots explore their environment efficiently without extrinsic rewards, similar to how children perform free play.

Before starting my PhD, I completed my Bachelor’s and Master’s degrees in Electrical Engineering and Information Technology at TU Munich. My specialization was in Robotics and Automation. During my studies, I worked on various machine learning projects spanning diverse fields such as robotics, signal processing, communications and neuroscience.

selected publications

2023

Regularity as Intrinsic Reward for Free Play

Cansu Sancaktar, Justus Piater, and Georg Martius

In Advances in Neural Information Processing Systems (NeurIPS), 2023

Bib HTML Website

@inproceedings{sancaktar2023regularity,
  title = {Regularity as Intrinsic Reward for Free Play},
  author = {Sancaktar, Cansu and Piater, Justus and Martius, Georg},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://openreview.net/forum?id=BHHrX3CRE1},
}

2022

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Cansu Sancaktar, Sebastian Blaes, and Georg Martius

In Advances in Neural Information Processing Systems (NeurIPS), 2022

Bib HTML Code Website

@inproceedings{Sancaktaretal22,
  title = {Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation},
  author = {Sancaktar, Cansu and Blaes, Sebastian and Martius, Georg},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://openreview.net/forum?id=NnuYZ1el24C},
}