Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation

Suraj Nair, Chelsea Finn

Abstract: Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor scalability of sampling-based planning optimizers, one significant limitation of these approaches is the ability to plan over long horizons to reach distant goals. To that end, we propose a framework for subgoal generation and planning, hierarchical visual foresight (HVF), which generates subgoal images conditioned on a goal image, and uses them for planning. The subgoal images are directly optimized to decompose the task into easy to plan segments, and as a result, we observe that the method naturally identifies semantically meaningful states as subgoals. Across three out of four simulated vision-based manipulation tasks, we find that our method achieves more than 20% absolute performance improvement over planning without subgoals and model-free RL approaches. Further, our experiments illustrate that our approach extends to real, cluttered visual scenes.

Code: https://github.com/suraj-nair-1/google-research/tree/master/hierarchical_foresight

Keywords: video prediction, reinforcement learning, planning

TL;DR: Hierarchical visual foresight learns to generate visual subgoals that break down long-horizon tasks into subtasks, using only self-supervision.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1909.05829/code)