Autonomous robots facing a diversity of open environments and performing a variety of tasks
and interactions need explicit deliberation in order to fulfill their missions. Deliberation is …

Multiagent systems are rapidly finding applications in a variety of domains, including
robotics, distributed control, telecommunications, and economics. The complexity of many …

Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Through multi-agent competition, the simple objective of hide-and-seek, and standard
reinforcement learning algorithms at scale, we find that agents create a self-supervised …

Deep reinforcement learning is the combination of reinforcement learning (RL) and deep
learning. This field of research has been able to solve a wide range of complex …

Similar to humans, RL agents use interactive learning to successfully obtain satisfactory
decision strategies. However, in many cases, it is desirable to learn directly from …

We consider the problem of constructing abstract representations for planning in high-
dimensional, continuous environments. We assume an agent equipped with a collection of …

We introduce an approach for deep reinforcement learning (RL) that improves upon the
efficiency, generalization capacity, and interpretability of conventional approaches through …

An intelligent agent interacting with the real world will encounter individual people, courses,
test results, drugs prescriptions, chairs, boxes, etc., and needs to reason about properties of …

Although deep reinforcement learning has become a promising machine learning approach
for sequential decision-making problems, it is still not mature enough for high-stake domains …