Mohamed Yassine Kabouri
I am a PhD student at LAAS-CNRS in the Gepetto team, working on Reinforcement Learning for Robotics.
Research interests Reinforcement Learning Robotics
News & Updates
New preprint: VAMPS: Visual and Motor Policies from Sampling-Based Planning. [arXiv] Website, code and video coming soon.
New preprint: CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning. [arXiv] [video] [code]
New blog post: Reinforcement Learning as Probabilistic Inference.
Our paper Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection has been accepted at IROS 2026! [arXiv] [video] [code]
I am visiting the Machines in Motion Lab for six months.
Publications
VAMPS: Visual and Motor Policies from Sampling-Based Planning
Preprint, 2026
- Sampling-Based Planning
- Policy Optimization
- Force-Aware Policy
- Robotics
CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning
Preprint, 2026
- Model-Based RL
- Robotics