Learning to act from actionless videos through dense correspondences
In this work, we present an approach to construct a video-based robot policy capable of
reliably executing diverse tasks across different robots and environments from few video …
reliably executing diverse tasks across different robots and environments from few video …
An unbiased look at datasets for visuo-motor pre-training
Visual representation learning hold great promise for robotics, but is severely hampered by
the scarcity and homogeneity of robotics datasets. Recent works address this problem by …
the scarcity and homogeneity of robotics datasets. Recent works address this problem by …
Imitation from observation: Learning to imitate behaviors from raw video via context translation
Imitation learning is an effective approach for autonomous systems to acquire control
policies when an explicit reward function is unavailable, using supervision provided as …
policies when an explicit reward function is unavailable, using supervision provided as …
From play to policy: Conditional behavior generation from uncurated robot data
While large-scale sequence modeling from offline data has led to impressive performance
gains in natural language and image generation, directly translating such ideas to robotics …
gains in natural language and image generation, directly translating such ideas to robotics …
Structured world models from human videos
We tackle the problem of learning complex, general behaviors directly in the real world. We
propose an approach for robots to efficiently learn manipulation skills using only a handful of …
propose an approach for robots to efficiently learn manipulation skills using only a handful of …
Language-driven representation learning for robotics
Recent work in visual representation learning for robotics demonstrates the viability of
learning from large video datasets of humans performing everyday tasks. Leveraging …
learning from large video datasets of humans performing everyday tasks. Leveraging …
One-shot imitation from observing humans via domain-adaptive meta-learning
Humans and animals are capable of learning a new behavior by observing others perform
the skill just once. We consider the problem of allowing a robot to do the same--learning …
the skill just once. We consider the problem of allowing a robot to do the same--learning …
Feature expansive reward learning: Rethinking human input
When a person is not satisfied with how a robot performs a task, they can intervene to correct
it. Reward learning methods enable the robot to adapt its reward function online based on …
it. Reward learning methods enable the robot to adapt its reward function online based on …
Actionable models: Unsupervised offline reinforcement learning of robotic skills
We consider the problem of learning useful robotic skills from previously collected offline
data without access to manually specified rewards or additional online exploration, a setting …
data without access to manually specified rewards or additional online exploration, a setting …
End-to-end robotic reinforcement learning without reward engineering
The combination of deep neural network models and reinforcement learning algorithms can
make it possible to learn policies for robotic behaviors that directly read in raw sensory …
make it possible to learn policies for robotic behaviors that directly read in raw sensory …