Attacca: goal-directed control for long-horizon embodied agents
An arXiv paper introduces Attacca, a method for training visual goal-conditioned policies for long-horizon embodied agents. It uses context-decoupled goal sampling to pair each demonstration with a class-compatible masked goal image from another world, adds a target-mask prediction head for dense current-view grounding, and conditions the policy on Search, Approach and Interact phases. On short- and long-horizon Minecraft tasks, the authors report 39.0–47.5% clean success, a 1.7–2.4x gain over the strongest baseline, and 54%, 30% and 28% completion on long-horizon tasks, up to a 7x improvement.
Because targets often lie outside the current view during long-horizon execution, modeling state continuity and search phases could matter for making embodied agents practical.