Cansu Sancaktar

5 papers · 2022–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13)

Venues

NeurIPS (3) ICML (2)

Top co-authors

Georg Martius (4) Sebastian Blaes (2) Albane Ruaud (1) Andreas Krause (1) Marco Bagatella (1) Stelian Coros (1) Andrii Zadaianchuk (1) Justus Piater (1) Christian Gumbsch (1) Pavel Kolev (1)

Research topics

Reinforcement Learning (4) Methods (3) Artificial Intelligence (2) Machine Learning (2) Applications (2) Deep Learning (1) Knowledge & Reasoning (1) Robotics (1) Architectures (1) Bayesian & Probabilistic (1) Capabilities (1) Core AI (1) Core Methods (1) Learning Paradigms (1) Learning Types (1)

Keywords

model-based reinforcement learning (2) zero-shot learning (1) robotic manipulation (1) epistemic uncertainty (1) object manipulation (1) gaussian process (1) optimal control (1) exploration policy (1) intrinsic motivation (1) dynamical system (1) vision-language model (1) zero-shot generalization (1) world model (1) intrinsic reward (1) permutation invariance (1) active exploration (1) semantic reward (1) model-based rl (1) zero-shot planning (1) combinatorial generalization (1)

Papers

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models ICML 2025 Modelling Microbial Communities with Graph Neural Networks ICML 2024 Optimistic Active Exploration of Dynamical Systems NeurIPS 2023 Regularity as Intrinsic Reward for Free Play NeurIPS 2023 Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation NeurIPS 2022