Binding Actions to Objects in World Models
This work addresses object-action binding in world models for robotics and AI, presenting incremental improvements with specific mechanisms.
The paper tackled the problem of binding actions to objects in object-factored world models by proposing soft and hard attention mechanisms, showing that hard attention improves object separation in grid-worlds and soft attention boosts performance in robotic manipulation tasks.
We study the problem of binding actions to objects in object-factored world models using action-attention mechanisms. We propose two attention mechanisms for binding actions to objects, soft attention and hard attention, which we evaluate in the context of structured world models for five environments. Our experiments show that hard attention helps contrastively-trained structured world models to learn to separate individual objects in an object-based grid-world environment. Further, we show that soft attention increases performance of factored world models trained on a robotic manipulation task. The learned action attention weights can be used to interpret the factored world model as the attention focuses on the manipulated object in the environment.