Hi ROS community,
We are organizing a 3-day Humanoid Robot Reinforcement Learning Bootcamp in Barcelona (June 17–19, 2026), focused on practical workflows for training and deploying control policies on humanoid robots.
The training is delivered by The Construct and is designed for engineers and researchers interested in reinforcement learning applied to humanoid systems.
During the bootcamp, participants will work through the main components of a sim-to-real pipeline:
-
RL-based walking control using Isaac Lab and MuJoCo
-
Whole-body control and motion imitation
-
Teleoperation and imitation learning with Isaac Mimic
-
Vision-Language-Action (VLA) models with Gr00t
-
Sim-to-sim validation and deployment on real robots
Participants will train and validate policies in simulation and deploy them on real humanoid robots (Unitree G1).
The format is fully practical, with all sessions focused on implementation and experimentation.
If relevant to your work, more details are available here:


