Onur Celik

Postdoc, Karlsruher Institut für Technologie

Joined

May 2021

Names

Onur Celik (Preferred)

Emails

****@kit.edu (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Postdoc

Karlsruher Institut für Technologie (kit.edu)

2025 – Present

PhD student

Karlsruhe Institute of Technology (kit.edu)

2020 – 2025

MS student

TU Darmstadt (tu-darmstadt.de)

2017 – 2019

Advisors, Relations & Conflicts

PhD Advisor

Neumann

2020 – Present

Expertise

Reinforcement Learning

Present

Policy Search for Robotics

Present

Diffusion Based Reinforcement Learning

Present

Publications

PAWS: Preference Learning with Advantage-Weighted Segments
Aleksandar Taranovic, Onur Celik, Niklas Freymuth, Ge Li, Serge Thilges, Tai Hoang, Rania Rayyes, Gerhard Neumann
- Submitted to ICLR 2026
- Readers: Everyone
Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns
Dong Tian, Onur Celik, Gerhard Neumann
- ICLR 2026 Poster
- Readers: Everyone
DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
- EWRL 2025 Poster
- Readers: Everyone
Scaffolding Dexterous Manipulation with Vision Language Models
Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum, Onur Celik, Aleksandar Taranovic, Denis Blessing, Gerhard Neumann, Jeannette Bohg, Dorsa Sadigh
- Dex-RSS-25
- Readers: Everyone
Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
- EXAIT@ICML 2025 Poster
- Readers: Everyone
Scaffolding Dexterous Manipulation with Vision-Language Models
Vincent de Bakker, Joey Hejna, Tyler Ga Wei Lum, Onur Celik, Aleksandar Taranovic, Denis Blessing, Gerhard Neumann, Jeannette Bohg, Dorsa Sadigh
- NeurIPS 2025 poster
- Readers: Everyone
Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
- WRL@ICLR 2025 Poster
- Readers: Everyone
DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing, Ge Li, Daniel Palenicek, Jan Peters, Georgia Chalvatzaki, Gerhard Neumann
- ICML 2025 poster
- Readers: Everyone
Perlin Noise for Exploration in Reinforcement Learning
Dominik Roth, Onur Celik, Fabian Otto, Gerhard Neumann
- Submitted to ICLR 2025
- Readers: Everyone
MaIL: Improving Imitation Learning with Selective State Space Models
Xiaogang Jia, Qian Wang, Atalay Donat, Bowen Xing, Ge Li, Hongyi Zhou, Onur Celik, Denis Blessing, Rudolf Lioutikov, Gerhard Neumann
- CoRL 2024
- Readers: Everyone

View all 27 publications

Co-Authors

View all 34 co-authors