In this work, we study generalized policy search-based methods with a focus on the score function used to guide the search over policies.
We present a strategy for designing and building very general robot manipulation systems involving the integration of a general-purpose task-and-motion planner with engineered and learned perception modules that estimate properties and affordances of unknown objects.
We conclude that learning to predict a sufficient set of objects for a planning problem is a simple, powerful, and general mechanism for planning in large instances.
1 code implementation • 9 Jul 2020 • Chuang Gan, Jeremy Schwartz, Seth Alter, Damian Mrowca, Martin Schrimpf, James Traer, Julian De Freitas, Jonas Kubilius, Abhishek Bhandwaldar, Nick Haber, Megumi Sano, Kuno Kim, Elias Wang, Michael Lingelbach, Aidan Curtis, Kevin Feigelis, Daniel M. Bear, Dan Gutfreund, David Cox, Antonio Torralba, James J. DiCarlo, Joshua B. Tenenbaum, Josh H. McDermott, Daniel L. K. Yamins
We introduce ThreeDWorld (TDW), a platform for interactive multi-modal physical simulation.
In contrast, deep reinforcement learning (DRL) methods use flexible neural-network-based function approximators to discover policies that generalize naturally to unseen circumstances.