Safety
Learning to See through Action: Predictive Curiosity for Robots
arXiv:2610.14302v1 Announce Type: new Abstract: Humans and animals do not learn vision from a fixed set of data: they move, interact, and learn from the visual consequences of their actions. Motivated
arXiv:2610.14302v1 Announce Type: new Abstract: Humans and animals do not learn vision from a fixed set of data: they move, interact, and learn from the visual consequences of their actions. Motivated by this developmental view, we study whether robots can improve visual learning by actively collecting experience through curiosity-driven interaction. We introduce DySCOVER, a self-supervised framework for active robot visual learning. A robot observes RGB frames, learns a visual autoencoder that encodes and reconstructs them, and trains a recurrent world model to predict the next visual latent state conditioned on the current state and action. The agent's policy is trained only with intrinsic rewards: reconstruction error encourages visually novel observations, while the world model's error encourages transitions whose consequences are not yet predictable. This prediction error biases the policy toward more intricate trajectories that enrich the agent's set of experiences with observations beyond those encouraged by visual novelty alone. Our experiments conducted with robotic arms as the embodied agents show that adding predictive curiosity improves the vision model over using visual curiosity alone. Across variations in initial conditions, experience capacity, embodiment, and scene content, adding predictive curiosity consistently improved visual learning. These results show that predictive curiosity can improve active visual learning beyond reconstruction-based curiosity alone.
Related
- Can Neural Networks Learn by Experimenting on Themselves? Self-Interventional Learning from Functional Consequences to Predictive Self-Knowledge
- Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
- Achieve What You Imagined: Learning to Align Actions with Visual Plans
- Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement
- Task Robustness via Re-Labelling Vision-Action Robot Data
Source: arXiv cs.LG | 2026-10-14