About me

I am a final year PhD student at the University of Alberta, working in Reinforcement Learning. I am fortunate to be advised by Matthew E. Taylor at the UofA. During my PhD, I have spent considerable time at MSR Montreal and New York, where I worked with Philip Bachman, Alex Lamb and John Langford. I also spent a year as a visiting scholar at UC Berkeley, where I was advised by Sergey Levine.

Previously, I was an AI resident at Facebook AI Research, Menlo Park, where I got the chance to work with Mohammad Ghavamzadeh. Even before, I was an undergraduate at IIT Madras, where I got introduced to RL research by Balaraman Ravindran.

Currently, I am working on efficient tokenization schemes for video prediction models, and on developing planning capabilities in language models.

I am on the industry job market currently. Please reach out if you think I’d be a good fit for any relevant research roles!

Contact me at my first name dot last name at gmail dot com

Research

Unified Auto-encoding with Masked Diffusion. Philippe Hansen-Estruch, Sriram Vishwanath, Amy Zhang, Manan Tomar. In Submission to NeurIPS, Arxiv, 2024.

Video Occupancy Models. Manan Tomar, Philippe Hansen-Estruch, Philip Bachman, Alex Lamb, John Langford, Matthew E Taylor, Sergey Levine. In Submission to NeurIPS, Arxiv, 2024.

Reward Centering. Abhishek Naik, Yi Wan, Manan Tomar, Rich Sutton. Reinforcement Learning Conference (RLC) 2024.

Robotic Offline RL from Internet Videos via Value-Function Pre-Training. Chethan Bhateja*, Derek Guo*, Dibya Ghosh*, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar. ICRA 2024.

Video-Guided Skill Discovery. Manan Tomar*, Dibya Ghosh*, Vivek Myers*, Anca Dragan, Matthew E Taylor, Philip Bachman, Sergey Levine. ICML Workshop on The Many Facets of Preference-Based Learning, 2023.

Ignorance is Bliss: Robust Control via Information Gating. Manan Tomar, Riashat Islam, Matthew E. Taylor, Sergey Levine, Philip Bachman. NeurIPS 2023.

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information. Riashat Islam*, Manan Tomar*, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford. ICML 2023.

Representation Learning in Deep RL via Discrete Information Bottleneck. Riashat Islam, Hongyu Zang, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, Alex Lamb. AISTATS 2023.

Learning Representations for Pixel-based Control: What Matters and Why?. Manan Tomar*, Utkarsh A. Mishra*, Amy Zhang, Matthew E. Taylor. TMLR 2022.

Learning Minimal Representations with Model Invariance. Manan Tomar, Amy Zhang, Matthew E. Taylor. Pre-print, 2021.

Model-Invariant State Abstractions for Model-based Reinforcement Learning. Manan Tomar, Amy Zhang, Roberto Calandra, Matthew E. Taylor, Joelle Pineau. Spotlight at Sparsity in Neural Networks workshop, 2021.

Mirror Descent Policy Optimization. Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh. Contributed talk at the DeepRL NeurIPS 2020 workshop; ICLR 2022.

Multi-step Greedy Reinforcement Learning Algorithms. Manan Tomar*, Yonathan Efroni*, Mohammad Ghavamzadeh. ICML 2020.

Successor Options : An Option Discovery Algorithm for Reinforcement Learning. Rahul Ramesh*, Manan Tomar*, Balaraman Ravindran. IJCAI 2019.

MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning. Manan Tomar, Akhil Sathuluri, Balaraman Ravindran. AAMAS 2019.