Planning is one of the most exciting uses of world models, but existing planners struggle on long horizons.
Introducing GRASP: a fast gradient-based planner for world models that outperforms prior methods on long-horizon tasks.
Two key ideas:
1.jointly optimize actions and intermediate subgoals
2.inject stochasticity to explore subgoal space
Project page:
Paper:
w/
@michaelpsenka @mikerabb @ask1729 and
@ylecun