• Publications
  • Influence
Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
TLDR
We present a deep RL method that is practical for real-world robotics tasks, such as robotic manipulation, and generalizes effectively to never-before-seen tasks and objects. Expand
  • 129
  • 14
  • PDF
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
TLDR
We present an approach for one-shot learning from a video of a human by using human and robot demonstration data from a variety of previous tasks to build up prior knowledge through meta-learning. Expand
  • 173
  • 11
  • PDF
Few-Shot Goal Inference for Visuomotor Learning and Planning
TLDR
We propose the few-shot objective learning problem, where the goal is to learn a task objective from only a few example images of successful end states. Expand
  • 27
  • 1
  • PDF
Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight
TLDR
We train a model with both a visual and physical understanding of multi-object interactions, and develop a sampling-based optimizer that can leverage these interactions to accomplish tasks. Expand
  • 39
  • PDF
Learning Predictive Models From Observation and Interaction
TLDR
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes. Expand
  • 11
  • PDF
Deep Reinforcement Learning amidst Lifelong Non-Stationarity
TLDR
We formalize this problem setting with the dynamic parameter Markov decision process and derive an off-policy RL algorithm that can reason about and tackle such lifelong non-stationarity. Expand
  • 7
  • PDF
Learning Latent Representations to Influence Multi-Agent Interaction
TLDR
We propose a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy. Expand
  • 3
  • PDF
Predict futures using video prediction model Training Time Test Time Collect Kinesthetic Demonstrations Autonomous Random Data
Machine learning has enabled robots to perform complex tasks in narrowly-scoped settings, and to perform simple tasks with high generalization. However, learning a model that can both perform complexExpand