AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

In reinforcement learning (RL), it is easier to solve a task if given a good representation.
While deep RL should automatically acquire such good representations, prior work often …

Reward specification is a notoriously difficult problem in reinforcement learning, requiring
extensive expert supervision to design robust reward functions. Imitation learning (IL) …

Many potential applications of reinforcement learning (RL) require guarantees that the agent
will perform well in the face of disturbances to the dynamics or reward function. In this paper …

We study the problem of learning a range of vision-based manipulation tasks from a large
offline dataset of robot interaction. In order to accomplish this, humans need easy and …

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 …

Abstract Model-based reinforcement learning (RL) has proven to be a data efficient
approach for learning control tasks but is difficult to utilize in domains with complex …

Policy gradients methods apply to complex, poorly understood, control problems by
performing stochastic gradient descent over a parameterized class of polices. Unfortunately …

Task specification is at the core of programming autonomous robots. A low-effort modality for
task specification is critical for engagement of non-expert end users and ultimate adoption of …