Article

SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Models

SafeDojo proposes a model-based safe reinforcement learning framework that improves vision-language-action (VLA) policies through world-model imagination, avoiding costly real-world exploration or reliance on hand-crafted safety functions. The method performs online reinforcement learning on top of an interactive video world model, using a ResNet success classifier to score predicted future frames, paired with a lightweight safety head that predicts per-step contact probabilities from the current latent context and candidate action chunks, then balances task execution and trajectory safety signals through Lagrangian-constrained GRPO.

Part of the event: SafeDojo Uses World-Model Imagination to Improve VLA Policy Safety

This page provides a summary and source link only.