publications

2024

  1. sensei-overview.png
    SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
    Cansu Sancaktar*, Christian Gumbsch*, Andrii Zadaianchuk, and 2 more authors
    In The Training Agents with Foundation Models Workshop at RLC, 2024
    * indicates equal contribution
  2. microbe_gnn.png
    Modelling Microbial Communities with Graph Neural Networks
    Albane Ruaud, Cansu Sancaktar, Marco Bagatella, and 2 more authors
    In ICML, 2024

2023

  1. grid_rair_videos.gif
    Regularity as Intrinsic Reward for Free Play
    Cansu SancaktarJustus Piater, and Georg Martius
    In Advances in Neural Information Processing Systems (NeurIPS), 2023
  2. Optimistic Active Exploration of Dynamical Systems
    Bhavya Sukhija, Lenart Treven, Cansu Sancaktar, and 3 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2023

2022

  1. cee_us_summary.gif
    Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
    Cansu SancaktarSebastian Blaes, and Georg Martius
    In Advances in Neural Information Processing Systems (NeurIPS), 2022

2020

  1. pixelai.png
    End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
    Cansu SancaktarMarcel A. J. Gerven, and Pablo Lanillos
    In 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 2020