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 …

With the growing integration of distributed energy resources (DERs), flexible loads, and
other emerging technologies, there are increasing complexities and uncertainties for …

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 …

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 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 …

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 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 …

Abstract We present CURL: Contrastive Unsupervised Representations for Reinforcement
Learning. CURL extracts high-level features from raw pixels using contrastive learning and …

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions
at an esports game. The game of Dota 2 presents novel challenges for AI systems such as …