Manan Tomar

Research

Publications and preprints.

Learning to Achieve Goals with Belief State Transformers

Conference | ICLR 2025

Edward S Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar, Ada Langford, Dinesh Jayaraman, Alex Lamb, John Langford

[arXiv]

Unified Auto-encoding with Masked Diffusion

Pre-print | 2024

Philippe Hansen-Estruch, Sriram Vishwanath, Amy Zhang, Manan Tomar

[arXiv]

Video Occupancy Models

Pre-print | 2024

Manan Tomar, Philippe Hansen-Estruch, Philip Bachman, Alex Lamb, John Langford, Matthew E Taylor, Sergey Levine

[arXiv]

Reward Centering

Conference | RLC 2024

Abhishek Naik, Yi Wan, Manan Tomar, Rich Sutton

[arXiv]

Robotic Offline RL from Internet Videos via Value-Function Pre-Training

Conference | ICRA 2024

Chethan Bhateja*, Derek Guo*, Dibya Ghosh*, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar

[arXiv]

Video-Guided Skill Discovery

Workshop | ICML Workshop on The Many Facets of Preference-Based Learning, 2023

Manan Tomar*, Dibya Ghosh*, Vivek Myers*, Anca Dragan, Matthew E Taylor, Philip Bachman, Sergey Levine

[pdf]

Ignorance is Bliss: Robust Control via Information Gating

Conference | NeurIPS 2023

Manan Tomar, Riashat Islam, Matthew E. Taylor, Sergey Levine, Philip Bachman

[arXiv]

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Conference | ICML 2023

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

[arXiv]

Representation Learning in Deep RL via Discrete Information Bottleneck

Conference | AISTATS 2023

Riashat Islam, Hongyu Zang, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, Alex Lamb

[arXiv]

Learning Representations for Pixel-based Control: What Matters and Why?

Journal | TMLR 2022

Manan Tomar*, Utkarsh A. Mishra*, Amy Zhang, Matthew E. Taylor

[arXiv]

Learning Minimal Representations with Model Invariance

Pre-print | 2021

Manan Tomar, Amy Zhang, Matthew E. Taylor

[pdf]

Model-Invariant State Abstractions for Model-based Reinforcement Learning

Workshop | Sparsity in Neural Networks workshop, 2021 (Spotlight)

Manan Tomar, Amy Zhang, Roberto Calandra, Matthew E. Taylor, Joelle Pineau

[arXiv]

Mirror Descent Policy Optimization

Conference | ICLR 2022 (Contributed talk at DeepRL NeurIPS 2020 workshop)

Manan Tomar, Lior Shani, Yonathan Efroni, Mohammad Ghavamzadeh

[arXiv]

Multi-step Greedy Reinforcement Learning Algorithms

Conference | ICML 2020

Manan Tomar*, Yonathan Efroni*, Mohammad Ghavamzadeh

[arXiv]

Successor Options: An Option Discovery Algorithm for Reinforcement Learning

Conference | IJCAI 2019

Rahul Ramesh*, Manan Tomar*, Balaraman Ravindran

[arXiv]

MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning

Conference | AAMAS 2019

Manan Tomar, Akhil Sathuluri, Balaraman Ravindran

[arXiv]