Sotabase

Career

· Postdoctoral Researcher, Microsoft2025–
· Research Intern, Microsoft2024–2024
· Research Intern, Microsoft2022–2022
· Visiting Scholar, University of California, Berkeley2022–2023
· Doctoral Student, University of Alberta2020–2025
· AI Resident, Facebook AI2019–2020
· Undergraduate Research Assistant, Indian Institute of Technology, Madras2017–2019
· Research Intern, Siemens Technology India2017–2018
· Producer, PopDev Studios2016–2017
· Virtual Reality Intern, Visionarch.co2016–2016
· Coordinator And Project Manager, Envisage, Shaastra, IIT Madras2015–2016
· Bachelor’s Degree, Engineering Design, Indian Institute of Technology, Madras2014–2019

Publications (27)

Mirror Descent Policy Optimization
International Conference on Learning Representations · 2020
102
cited
Successor Options: An Option Discovery Framework for Reinforcement Learning
International Joint Conference on Artificial Intelligence · 2019
39
cited
Model-Invariant State Abstractions for Model-Based Reinforcement Learning
arXiv.org · 2021
33
cited
Learning Representations for Pixel-based Control: What Matters and Why?
Trans. Mach. Learn. Res. · 2021
31
cited
Robotic Offline RL from Internet Videos via Value-Function Pre-Training
arXiv.org · 2023
29
cited
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
arXiv.org · 2022
21
cited
Reward Centering
RLJ · 2024
15
cited
Multi-step Greedy Reinforcement Learning Algorithms
International Conference on Machine Learning · 2019
14
cited
Ignorance is Bliss: Robust Control via Information Gating
Neural Information Processing Systems · 2023
13
cited
Principled Offline RL in the Presence of Rich Exogenous Information
International Conference on Machine Learning · 2022
11
cited
Representation Learning in Deep RL via Discrete Information Bottleneck
International Conference on Artificial Intelligence and Statistics · 2022
11
cited
Robotic Offline RL from Internet Videos via Value-Function Learning
IEEE International Conference on Robotics and Automation · 2024
11
cited
Learning to Achieve Goals with Belief State Transformers
arXiv.org · 2024
10
cited
The Belief State Transformer
International Conference on Learning Representations · 2024
8
cited
Successor Options : An Option Discovery Algorithm for Reinforcement Learning
2018
5
cited
DM-Codec: Distilling Multimodal Representations for Speech Tokenization
Conference on Empirical Methods in Natural Language Processing · 2024
4
cited
MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning
Adaptive Agents and Multi-Agent Systems · 2019
4
cited
Video Occupancy Models
arXiv.org · 2024
4
cited
Video-Guided Skill Discovery
3
cited
Multi-step Greedy Policies in Model-Free Deep Reinforcement Learning
arXiv.org · 2019
1
cited
Sotabase
Manan Tomar | Researcher Profile | Sotabase | Sotabase