Baohe Zhang

Baohe Zhang

PhD Candidate

University of Freiburg

Biography

I’m a PhD candidate under the supervision of Prof. Joschka Bödecker and Prof. Thomas Brox at the University of Freiburg. My research interests include reinforcement learning, automated machine learning and the applications of machine learning techniques in robotics.

Interests
  • Reinforcement Learning
  • Automated Machine Learning
  • Robotics
Education

  • PhD Candidate, until now

    University of Freiburg

  • Master of Science, 2021

    University of Freiburg

  • Bachelor of Science, 2018

    Tongji University

Recent Publications

Fitting Reinforcement Learning Model to Behavioral Data under Bandits
Investigates fitting RL models to behavioral data under bandit feedback, proposing a new method and demonstrating its effectiveness.
PDF
Constrained Reinforcement Learning with Smoothed Log Barrier Function
Proposes a Smoothed Log Barrier Function (CSAC-LB) for constrained RL, proving convergence to the optimal policy and demonstrating effectiveness on safety-critical tasks.
PDF Code
Goal Achievement Guided Exploration: Mitigating Premature Convergence in Learning Robot Control
Proposes Goal Achievement Guided Exploration (GAGE) to mitigate premature convergence and improve sample efficiency in learning robot control with sparse rewards.
PDF
Constrained Reinforcement Learning for Safe Heat Pump Control
Applies Constrained Reinforcement Learning to heat pump control, minimizing energy consumption while ensuring comfort and safety.
PDF
Revisiting Safe Exploration in Safe Reinforcement learning
Introduces a new safety metric, expected maximum consecutive cost steps (EMCC), to address limitations in standard SafeRL cost metrics and improve safe exploration.
PDF
See all publications

Experience

 
 
 
 
 
Visiting Student
LASR Lab, TU Dresden
Dec 2025 – Mar 2026 Dresden, Germany
Internship working on Dexterous Hand Manipulation, supervised by Prof. Roberto Calandra.
LASR Lab, TU Dresden
 
 
 
 
 
Visiting Student
Inria Paris Willow
Sep 2025 – Nov 2025 Paris, France
Internship working on World Model and Planning. Supervised by Dr. Shizhe Chen.
Inria Paris Willow
 
 
 
 
 
PhD Candidate
University of Freiburg
Apr 2021 – Present Freiburg, Germany
Focusing on Reinforcement Learning, Automated Machine Learning, and Robotics. Supervised by Prof. Joschka Bödecker and Prof. Thomas Brox.
University of Freiburg
 
 
 
 
 
Master Student
University of Freiburg
Jan 2018 – Mar 2021 Freiburg, Germany
Studied Computer Science. Thesis supervised by Prof. Frank Hutter and Prof. Roberto Calandra.
University of Freiburg
 
 
 
 
 
Undergraduate Student
Tongji University
Sep 2013 – Jan 2018 Shanghai, China
Studied Mechatronics Engineering, exchanged to HTW Saar for the last year. Thesis written in Forschungszentrum Informatik Karlsruhe.
Tongji University

Contact