I am a researcher in the Reinforcement Learning group at Microsoft Research AI, Redmond, USA. I also work closely with the Reinforcement Learning groups at MSR NYC and the research team of Microsoft Chief Science Officer, Eric Horvitz.

I finished my PhD at the Robotics Institute, Carnegie Mellon University, USA, where I was advised by Prof. J. Andrew (Drew) Bagnell. I do fundamental as well as applied research in machine learning, control and computer vision with applications to autonomous agents in general and robotics in particular.

My interests include decison-making under uncertainty, reinforcement learning, artificial intelligence and machine learning. I regularly area-chair/review for NeurIPS, ICLR, ICML. On occasion for ICRA, IROS, IJRR, JFR, CVPR, ECCV, ICCV.


  • Reinforcement Learning
  • Robotics
  • Planning
  • Vision
  • AutoML


  • PhD in Robotics, 2015

    Carnegie Mellon University

  • MS in Robotics, 2012

    Carnegie Mellon University

  • Bachelor of Electrical Engineering, 2007

    Delhi College of Engineering



Principal Researcher

Microsoft Research AI

Aug 2019 – Present Redmond, Washington

Senior Researcher

Microsoft Research AI

Jul 2015 – Aug 2019 Redmond, Washington

PhD Student

Robotics Institute, Carnegie Mellon University

Jul 2010 – Jul 2015 Pittsburgh, Pennsylvania



Aditya Modi

University of Michigan, Summer 2018


Alex LaGrassa

CMU, Summer 2020


Angela Lin

University of Texas, Summer 2019


Artem Rozantsov

EPFL, Summer 2016


Benjamin Hepp

ETH Zurich, Summer 2017


Brian Axelrod

Stanford University, Summer 2016


Dilip Arumugam

Stanford University, Summer 2019


Elizabeth Bondi

Harvard University, Fall 2017


Felix Berkenkamp

ETH Zurich, Summer 2017


Francisco Garcia

University of Massachusetts, Fall 2016


Hanzhang Hu

CMU, Summer 2018


Khanh Nguyen

UMD, Summer 2018


Mike Roberts

Stanford University, Summer 2016, 2017


Ramya Ramakrishnan

MIT, Summer 2017, 2018


Sanjiban Choudhury

CMU, Summer 2016


Shushman Choudhury

Stanford University, Summer 2020


Simon Ramstedt

MILA, Summer 2017


Wen Sun

CMU, Summer 2016


  • 03/2020: Area chair for Neurips 2020.
  • 06/2020: Invited talk on  Robotics with Vision-in-the-Loop at  CVPR 2020 Workshop on Fair, Data-Efficient and Trusted CV 
  • 02/2020: MSR podcast on my research journey!
  • 11/2019: Area chair for ICML 2020.
  • 11/2019: Using RL to optimize software pipelines accepted at AAAI 2020.
  • 10/2019: Invited to NSF Panel on Robotics and Speech at UMD.
  • 09/2019: Efficient Forward Architecture Search accepted to NeurIPS 2019.
  • 09/2019: Top 50% reviewer at NeurIPS  2019.
  • 06/2019:  MSR blog post on visual navigation via language assistance.
  • 05/2019:  Efficient Forward Neural Architecture Search paper and  code is public.
  • 04/2019: Metareasoning in Modular Software Systems using RL is public, Real-World RL ICML workshop and AAAI 2020.
  • 03/2019: Paper on visual navigation via language assistance accepted to CVPR 2019.
  • 02/2019: Outstanding reviewer award ICLR 2019.
  • 01/2019: Invited to CCC-NSF Robotics and Learning Workshop in San Francisco.
  • 10/2018: Invited talk on Interactive Machine Learning at UMD.
  • 10/2018: Two papers accepted at AAAI 2019. Anytime Neural Networks selected for oral presentation. 
  • 10/2018: Top reviewer award NeurIPS 2018.
  • 09/2018: Invited talk on Robotics and Imitation Learning at New York University. 
  • 09/2018: Invited talk on Imitation Learning at Reinforcement Learning Day at MSR New York.
  • 08/2018: Organizer of session on ‘AI for AI Systems’ at MSR Faculty Summit 2018.
  • 07/2018: Invited talk at UW-MSR Summer Retreat on Social Robotics.
  • 06/2018: Paper on Learning 3D View Utilities accepted at ECCV 2018.
  • 06/2018: Invited talk at RSS Workshop on Resilient Robotics.
  • 02/2018: Paper on Blind Spots in RL accepted to AAMAS 2018.
  • 02/2018: Journal version of Learning to Gather Information accepted at IJRR.
  • 01/2018: Invited talk at The Robotics Institute, Carnegie Mellon University.
  • 12/2017: Visiting MSR Bangalore.
  • 10/2017: Upcoming invited talk at ICCV 2017 Workshop on Role of Simulation in Computer Vision.
  • 08/2017: Paper on efficient 3D scanning accepted at ICCV 2017.
  • 07/2017: Paper describing AirSim accepted at FSR 2017.
  • 06/2017: Invited talk at International Symposium on Aerial Vehicles at University of Pennsylvania.
  • 05/2017: Paper on efficient route planning leveraging multi-armed bandits accepted at ICML 2017.
  • 04/2017: Paper on adaptive information gathering accepted at RSS 2017.
  • 03/2017: Paper on UAV tracking using flight dynamics accepted for oral presentation at CVPR 2017.
  • 02/2017: We released open-source photo-realistic robotics simulator  AirSim.
  • 01/2017: Two papers accepted at ICRA 2017.
  • 12/2016: Sponsorship and Publicity Chair of Conference on Robot Learning.
  • 10/2016: Invited talk at workshop on “Vision-based High Speed Autonomous Navigation of UAVs”, IROS 2017.
  • 08/2016: Invited to NSF-UAS Advisory Board meeting at Dayton, OH.
  • 07/2016: Co-organized workshop on “Safe-Cyber Physical Systems” at Faculty Summit, Microsoft Research.
  • 06/2016: Presented at RSS Workshop on Task and Motion Planning at University of Michigan, Ann Arbor.
  • 10/2015: Trajectory optimization for Team Chambliss at Red Bull Air Race at Dallas, TX.
  • 08/2015: Joined Microsoft Research.
  • 07/2015: Defended PhD thesis at Carnegie Mellon University.


Quickly discover relevant content by filtering publications.

Efficient forward architecture search

We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers. …

Anytime neural networks via joint optimization of auxiliary losses

This work considers the trade-off between accuracy and test-time computational cost of deep neural networks (DNNs) via mph{anytime} …

Overcoming blind spots in the real world: Leveraging complementary abilities for joint execution

Simulators are being increasingly used to train agents before deploying them in real-world environments. While training in simulation …

Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention

We present Vision-based Navigation with Languagebased Assistance (VNLA), a grounded vision-language task where an agent with visual …

Discovering blind spots in reinforcement learning

Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These …

Learn-to-score: Efficient 3d scene exploration by predicting view utility

Camera equipped drones are nowadays being used to explore large scenes and reconstruct detailed 3D maps. When free space in the scene …

Submodular trajectory optimization for aerial 3d scanning

Drones equipped with cameras are emerging as a powerful tool for large-scale aerial 3D scanning, but existing automatic flight planners …

Airsim: High-fidelity visual and physical simulation for autonomous vehicles

Developing and testing algorithms for autonomous vehicles in real world is an expensive and time consuming process. Also, in order to …

Adaptive information gathering via imitation learning

In the adaptive information gathering problem, a policy is required to select an informative sensing location using the history of …

Safety-aware algorithms for adversarial contextual bandit

In this work we study the safe sequential decision making problem under the setting of adversarial contextual bandits with sequential …

Learning to gather information via imitation

The budgeted information gathering problem - where a robot with a fixed fuel budget is required to maximize the amount of information …

Vision and learning for deliberative monocular cluttered flight

Cameras provide a rich source of information while being passive, cheap and lightweight for small and medium Unmanned Aerial Vehicles …

Predicting Sets and Lists: Theory and Practice

Increasingly, real world problems require multiple predictions while traditional supervised learning techniques focus on making a …

Predicting multiple structured visual interpretations

We present a simple approach for producing a small number of structured visual outputs which have high recall, for a variety of tasks …

Gauss Meets Canadian Traveler: Shortest-Path Problems with Correlated Natural Dynamics

In a variety of real world problems from robot navigation to logistics, agents face the challenge of path optimization on a graph with …

Knapsack constrained contextual submodular list prediction with application to multi-document summarization

Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a …

Learning monocular reactive uav control in cluttered natural environments

Autonomous navigation for large Unmanned Aerial Vehicles (UAVs) is fairly straight-forward, as expensive sensors and monitoring devices …

Classification of plant structures from uncalibrated image sequences

This paper demonstrates the feasibility of recovering fine-scale plant structure in 3D point clouds by leveraging recent advances in …

Contextual Sequence Prediction with Application to Control Library Optimization

Sequence optimization, where the items in a list are ordered to maximize some reward has many applications such as web advertisement …

Efficient Optimization of Control Libraries

A popular approach to high dimensional control problems in robotics uses a library of candidate “maneuvers” or “trajectories”. The …