Counterintuitive as it may seem, a lot can be done for RL without rewards! Examples: goal-conditioned RL, unsupervised RL, exploration, world modeling... If you are working on these directions, consider submitting to the RLBrew workshop at RLC!

I'm sadly unable to be at #RSS2025 this year, but my students Arhan Jain, Chuning Zhu and Marcel Torné will be! Find them presenting some exciting work today, 6/21: 1) Chuning Zhu will present Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large

Excited about this project where we cast VQA into world models! Check out the website demo!