MazeExplorer [1.0.0]
MazeExplorer is a customisable 3D benchmark for assessing generalisation in Reinforcement Learning. It is based on the 3D first-person game Doom and the open-source environment VizDoom. This repository contains the code for the MazeExplorer Gym…
VNLA via Imitation Learning with Indirect Intervention
We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates a real-world scenario…
2019 Dissertation Grant recipients embarking on diverse paths to scientific and societal impact
I’m pleased to announce the winners of the 2019 Microsoft Research Dissertation Grants. Each dissertation grant provides up to $25,000 in funding to doctoral students at North American universities who are underrepresented in the field…
AI for Earth’s Land Cover Mapping
High-resolution land cover mapping is a process of assigning land use labels, such as “impervious surface,” or “tree canopy” to each pixel in high resolution (<1m) aerial or satellite imagery. Such maps are an essential…
Microsoft at ICML 2019
Microsoft is excited to be a Gold sponsor of ICML. We will have over 100 Microsoft attendees present at the conference. Stop by our booth (#310) to chat with our experts, see demos of our…
Dead-ends and Secure Exploration in Reinforcement Learning [1.0]
This repository hosts the code for the following ICML 2019 paper: Dead-ends and Secure Exploration in Reinforcement Learning