Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by @jiazhi_yang2024 et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with @chris_j_paxton and @DJiafei, to learn more!

3 of us @micoolcho @chris_j_paxton @DJiafei are super excited to help organize the Robotic Origami Competition at IROS (Sept 2026), along with @BitRobotNetwork @SharpaRobotics @LightwheelAI @hq_fang @sanatem @Noriaki_Hirose @gao_young Calling for teams!

Interested to learn more? Register for our info sessions here: robotic-origami-challenge.gi…