Abstract Model quantization is a promising approach to compress deep neural networks and
accelerate inference, making it possible to be deployed on mobile and edge devices. To …

Pre-training on Internet data has proven to be a key ingredient for broad generalization in
many modern ML systems. What would it take to enable such capabilities in robotic …

To build general robotic agents that can operate in many environments, it is often imperative
for the robot to collect experience in the real world. However, this is often not feasible due to …

Despite the success of reinforcement learning methods, they have yet to have their
breakthrough moment when applied to a broad range of robotic manipulation tasks. This is …

The current dominant paradigm for imitation learning relies on strong supervision of expert
actions to learn both'what'and'how'to imitate. We pursue an alternative paradigm wherein an …

We introduce VIOLA, an object-centric imitation learning approach to learning closed-loop
visuomotor policies for robot manipulation. Our approach constructs object-centric …

A highly desirable property of a reinforcement learning (RL) agent--and a major difficulty for
deep RL approaches--is the ability to generalize policies learned on a few tasks over a high …

Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw
sensory inputs, but have yet to achieve the kind of broad generalization and applicability …

Sharing autonomy between robots and human operators could facilitate data collection of
robotic task demonstrations to continuously improve learned models. Yet, the means to …

Robotic reinforcement learning (RL) holds the promise of enabling robots to learn complex
behaviors through experience. However, realizing this promise for long-horizon tasks in the …