Florian Vogt

Hej! I am a Research Engineer at KTH Royal Institute of Technology in Stockholm, where I work on Reinforcement Learning.

I received my Master's degree from the University of Freiburg. I now want to focus on applying Reinforcement Learning to real-world applications.

I love solving problems that require an effort in both research and engineering. My work mostly focuses on sample and computational efficient RL, scaling it effectively for challenging tasks.

This effort resulted in XQC, a state-of-the-art algorithm in off-policy RL that achieves its performance through surprisingly simple methods.

Email / GitHub / Scholar

Research

	FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control Donghu Kim, Youngdoo Lee, Minho Park, Kinam Kim, Aswin Nahrendra, Takuma Seno, Sehee Min, Daniel Palenicek, Florian Vogt, Danica Kragic, Jan Peters, Jaesik Choo, Honglak Lee Robotics: Science and Systems (RSS), 2026 Project Page / Code / ArXiv Optimizing SAC for high-speed robotics training. Adopted as a baseline for high-dimensional robotic benchmarks.
	XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning Daniel Palenicek, Florian Vogt, Joe Watson, Ingmar Posner, Jan Peters International Conference on Learning Representations (ICLR), 2026 Project Page / Code / ArXiv Accelerating training by improving the conditioning of the optimization landscape in deep RL.
	Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization Daniel Palenicek, Florian Vogt, Joe Watson, Jan Peters NeurIPS, 2025 ArXiv A study on how normalization stabilizes and scales off-policy learning for complex tasks.
	Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization Sascha Marton, Tim Grams, Florian Vogt, Stefan Luedtke, Christian Bartelt, Heiner Stuckenschmidt International Conference on Learning Representations (ICLR), 2025 Code / ArXiv Handles information bottleneck issues in tree-structured RL via direct optimization.