GRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3) reshaping gradients so actions get clean signals while we avoi...
Receive updates from The Berkeley Artificial Intelligence Research Blog for free, starting right now.
We can deliver them by email, via your phone or you can read them from a personalised news page on follow.it.
This way you won't miss any new article from The Berkeley Artificial Intelligence Research Blog. Unsubscribe at any time.
Site title: Berkeley Artificial Intelligence Research Lab