Tanmay Gangwani

I am a principal applied scientist at Microsoft, where I build collaborative AI agents that power intelligent experiences in Microsoft Teams.

Previously, I was at Amazon, where I worked on architectures and methods for personalized search, product ranking, and recommendation at scale. I hold a Ph.D. from the University of Illinois Urbana-Champaign, where my research focused on applied reinforcement learning and imitation learning algorithms (thesis), and an M.S. from the same institution, where I worked at the intersection of computer architecture and compilers (thesis).

LinkedIn  /  Google Scholar  /  X  /  Email  

Publications

Publications through 2022; for some work beyond that, see Google Scholar
Hindsight Foresight Relabeling for Meta-Reinforcement Learning
Michael Wan, Jian Peng, Tanmay Gangwani
International Conference on Learning Representations (ICLR), 2022
[code] [video]
Imitation Learning from Observations under Transition Model Disparity
Tanmay Gangwani, Yuan Zhou, Jian Peng
International Conference on Learning Representations (ICLR), 2022
Learning Guidance Rewards with Trajectory-space Smoothing
Tanmay Gangwani, Yuan Zhou, Jian Peng
Conference on Neural Information Processing Systems (NeurIPS), 2020
[code] [poster] [video]
Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
Tanmay Gangwani, Jian Peng, Yuan Zhou
Conference on Robot Learning (CoRL), 2020
[code] [slides] [video]
State-only Imitation with Transition Dynamics Mismatch
Tanmay Gangwani, Jian Peng
International Conference on Learning Representations (ICLR), 2020
[code] [slides] [video]
Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
Michael Wan, Tanmay Gangwani, Jian Peng
The Conference on Uncertainty in Artificial Intelligence (UAI), 2020
[slides] [video]
Learning Belief Representations for Imitation Learning in POMDPs
Tanmay Gangwani, Joel Lehman, Qiang Liu, Jian Peng
The Conference on Uncertainty in Artificial Intelligence (UAI), 2019
[code]
Learning Self-Imitating Diverse Policies
Tanmay Gangwani, Qiang Liu, Jian Peng
International Conference on Learning Representations (ICLR), 2019
[code] [slides] [poster]
Policy Optimization by Genetic Distillation
Tanmay Gangwani, Jian Peng
International Conference on Learning Representations (ICLR), 2018
[poster]
Distributed and Secure ML using Self-tallying Multi-party Aggregation
Yunhui Long*, Tanmay Gangwani*, Haris Mughees, Carl Gunter
(* denotes equal contribution)
NeurIPS workshop on Privacy Preserving Machine Learning (PPML), 2018
[code] [slides]
Architectural Support for Relaxed Concurrent Priority Queueing in Chip Multiprocessors
Azin Heidarshenas*, Tanmay Gangwani*, Serif Yesil, Adam Morrison, Josep Torrellas
(* denotes equal contribution)
International Conference on Supercomputing (ICS), 2020
[slides]
Breaking Serialization in Lock-Free Multicore Synchronization
Tanmay Gangwani, Adam Morrison, Josep Torrellas
Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2016
[poster] [slides]

Website design borrowed from here