We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used explicit models.
This task space can be quite general and abstract; its only requirements are to be sampleable and to well-cover the space of useful tasks.
Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often impractical in open-world environments.
We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks.
We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics.
Mutual information maximization has emerged as a powerful learning objective for unsupervised representation learning obtaining state-of-the-art performance in applications such as object recognition, speech recognition, and reinforcement learning.
In this work we explore a new approach for robots to teach themselves about the world simply by observing it.
While representations are learned from an unlabeled collection of task-related videos, robot behaviors such as pouring are learned by watching a single 3rd-person demonstration by a human.
Ranked #3 on Video Alignment on UPenn Action
As a result, the task of ranking search results automatically (learning to rank) is a multibillion dollar machine learning problem.