Robot Learning Paper Club - The RL post-training edition.

Robot learning in Zurich is scattered. Academia, big tech, and startups are all pushing the field forward, but rarely in the same room. If Zurich is going to lead in robotics globally, the people building it need to talk to each other. This is a space for exactly that. We mix 10-minute presentations from researchers in the local community presenting their own work and participants presenting recent papers they thought were interesting (5 minutes). Spots are limited. Contributing participants and people who have presented in the past have preferred access. ----- RL post-training edition: This edition focuses on RL methods for post-training VLAs and world models. Topics we think are interesting: RL on top of pretrained VLAs: RL tokens, residual policies, offline-to-online RL Reward models and value functions for real-robot tasks RL inside learned world models, or world models used as reward signals Sample efficiency and safety when running RL on real hardware Want to present a paper but not sure which one? Feel free to reach out to us at [email protected] and we can help you find one!