Conversational Agents that See
In this project we explore what it might mean to augment digital agents such as Microsoft Cortana with the ability to see. By partnering with experts in computer vision, speech and machine learning, we ask whether…
Machine Learning Systems for Highly Distributed and Rapidly Growing Data
The usability and practicality of machine learning are largely influenced by two critical factors: low latency and low cost. However, achieving low latency and low cost is very challenging when machine learning depends on real-world…
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
Probabilistic Q-learning is a promising approach balancing exploration and exploitation in reinforcement learning. However, existing implementations have significant limitations: they either fail to incorporate uncertainty about long-term consequences of actions or ignore fundamental dependencies in…
First TextWorld Problems Challenge – Getting Started
Enter the competition First TextWorld Problems: A Reinforcement and Language Learning Challenge at aka.ms/textworld-challenge. Follow the 6-step guide in the video to get started. See if you can build an agent that wins at a…
Azure Research – Security and Privacy
Security and privacy are arguably the most significant concerns for enterprises and consumers using public cloud platforms. The confidential computing theme at Microsoft Research Cambridge has been conducting pioneering research in the design of systems…
Advancing Human-Centered AI
We’re excited about the formal launch of the Stanford Institute for Human-Centered Artificial Intelligence (HAI) on Monday, March 18th. We resonate with Fei-Fei Li, John Etchemendy, and other leaders at Stanford on the promise of…
Getting Started with TextWorld
TextWorld is a text-based game generator and sandbox learning environment for reinforcement learning agents. Watch this video to get started with using TextWorld! Learn more about the competition at aka.ms/textworld-challenge