Publications

An Alternate Policy Gradient Estimator for Softmax Policies. [PDF]
Shivam Garg, Samuele Tosatto, Yangchen Pan, Martha White, A. Rupam Mahmood.
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

A General Class of Surrogate Functions for Stable and Efficient Reinforcement Learning. [PDF]
Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Müller, Shivam Garg, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux.
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
[Nominated for the Best Paper Award]

Gradient Temporal-Difference Learning with Regularized Corrections. [PDF]
Sina Ghiassian, Andrew Patterson, Shivam Garg, Dhawal Gupta, Adam White, Martha White.
International Conference on Machine Learning (ICML), 2020.

Object Sequences: Encoding Categorical and Spatial Information for a Yes/No Visual Question Answering Task. [PDF] [DOI]
Shivam Garg, Rajeev Srivastava.
IET Computer Vision, 2018.

Workshop Papers

Making Policy Gradient Estimators for Softmax Policies More Robust to Non- stationarities. [PDF]
Shivam Garg, Samuele Tosatto, Yangchen Pan, Martha White, A. Rupam Mahmood.
The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022.

Enabling Safe Exploration of Action Space in Real--World Robots. [PDF]
Shivam Garg, Homayoon Farrahi, A. Rupam Mahmood.
Virtual Conference on Reinforcement Learning for Real Life (RL4RealLife), 2020.

Mirror Descent for Robust Reinforcement Learning. [PDF]
Shivam Garg.
Indian Workshop on Machine Learning (iWML), 2018.

Theses

Analysis of an Alternate Policy Gradient Estimator for Softmax Policies. [PDF]
Shivam Garg.
M.Sc. Thesis, University of Alberta, 2021.
[Co-winner of the Best Master's Thesis Award 2022, Canadian AI Association]

Coordinated Exploration for Concurrent Reinforcement Learning. [PDF]
Shivam Garg.
M.Tech. Thesis, Indian Institute of Technology (BHU) Varanasi, 2019.