Firas Al-Hafez

Research Interests
Reinforcement Learning, Imitation Learning, Robot Learning, Locomotion.
Affiliation
TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
Contact
firas.al-hafez@tu-darmstadt.de
Room E303, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-20811
Firas joined the Intelligent Autonomous System lab on November, 1st, 2021 as a PhD student. He focuses on neuromuscular gait control using inverse reinforcement learning with application on exoskeletons and humanoids. He works with Davide Tateo and Jan Peters within IAS and its research group Safe and Reliable Robot Learning. Previously, he received MSc degrees in Electronic Systems and Mechanical Engineering, as well as a BSc degree in Industrial Engineering field Mechanical Engineering from TU Braunschweig.
During his studies, he completed several applied projects, including a master's thesis on the "Comparison of Reinforcement Learning Algorithms and Evolution Strategies on Robot Manipulation Tasks" at the IRP under the supervision of Jochen Steil and a master's thesis on the "Development of a Tactical Maneuver Planner for Automated Driving Systems in Urban Areas using Reinforcement Learning" at the Volkswagen Group.
Publications
- Al-Hafez, F.; Tateo, D.; Arenz, O.; Zhao, G.; Peters, J. (2023). LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning, International Conference on Learning Representations (ICLR).
- Al-Hafez, F.; Tateo, D.; Arenz, O.; Zhao, G.; Peters, J. (2023). Least Squares Inverse Q-Learning, European Workshop on Reinforcement Learning (EWRL).
- Al-Hafez, F.; Zhao, G.; Peters, J.; Tateo, D. (2023). LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion, Robot Learning Workshop, Conference on Neural Information Processing Systems (NeurIPS).
- Al-Hafez, F.; Steil, J. (2021). Redundancy Resolution as Action Bias in Policy Search for Robotic Manipulation, 5th Conference on Robot Learning (CoRL).