Reinforcement Learning for Quadrotor Using AirSim

November 10, 2017
Shital Shah, Ashish Kapoor | Microsoft Research

Example of reinforcement learning with quadrotors using AirSim and CNTK by Ashish Kapoor

- Ashish Kapoor
  
  General Manager, Autonomous Systems and Robotics Group
- Shital Shah
  
  Principal Research Engineer
Research Area
Research Lab
- Microsoft Research Lab - Redmond
Project
- Aerial Informatics and Robotics Platform

Watch Next

Introducing Muse: Our first generative AI model designed for gameplay ideation
May 20, 2026
Guiding the AI disruption to the Good Place
May 14, 2026
Yash Lara,

David Rothschild
New fine-tuning of language models: Match meaning, not tokens
May 14, 2026
Yash Lara,

Carles Domingo-Enrich
Introducing Interwhen: Steering reasoning agents with real-time verification
May 14, 2026
Yash Lara,

Amit Sharma
Introducing GitHub Agentic Workflows: AI that runs your repo
May 14, 2026
Yash Lara,

Peli de Halleux
MagenticLite: A full-stack agentic experience powered by Small Models
May 14, 2026
Harkirat Behl,

Weili Shi,

Hussein Mozannar
Generative AI for High-Stakes Decision-Making with Applications in One Health
May 12, 2026
Lingkai Kong
Physics and information theory of generative diffusion
May 5, 2026
Luca Ambrogioni
Language & Voice AI for Africa: From Data to Deployment and Impact
April 30, 2026
Vukosi Marivate,

Tavonga Siyavora,

Tobi Olatunji

, et. al.
Upper Bound 2024: Towards Human-Centered AI in AAA Video Game
June 11, 2024
Raluca Georgescu

Your Privacy Choices