AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

Data availability and accessibility have brought in unseen changes in the finance systems
and new theoretical and computational challenges. For example, in contrast to classical …

In this work, we address challenging multi-agent cooperation problems with decentralized
control, raw sensory observations, costly communication, and multi-objective tasks …

We introduce DeepNash, an autonomous agent that plays the imperfect information game
Stratego at a human expert level. Stratego is one of the few iconic board games that artificial …

Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for
training models with broad, general capabilities for text, images, and other modalities …

Compute, data, and algorithmic advances are the three fundamental factors that drive
progress in modern Machine Learning (ML). In this paper we study trends in the most readily …

The advances in reinforcement learning have recorded sublime success in various domains.
Although the multi-agent domain has been overshadowed by its single-agent counterpart …

The field of explainable artificial intelligence (XAI) aims to bring transparency to today's
powerful but opaque deep learning models. While local XAI methods explain individual …

We present Habitat 3.0: a simulation platform for studying collaborative human-robot tasks in
home environments. Habitat 3.0 offers contributions across three dimensions:(1) Accurate …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …