Sotabase

Career

· AI Research Scientist, Meta2025–
· Senior Research Scientist, Apple2024–2025
· Applied Scientist II, Amazon2023–2024
· Research Scientist Intern, DeepMind2021–2021
· Research Intern, JPMorgan Chase & Co.2020–2021
· Research Intern, NVIDIA2019–2020
· Student Entrepreneur, Student Entrepreneurs’ Programme (StEP), Oxford University Innovation (OUI)2019–2019
· Research Scientist, Xerox Research Centre2016–2017
· Research Intern, Xerox Research Centre2014–2014
· Bachelor of Technology - BTech, Computer Science, Indian Institute of Technology, Delhi
· Master of Technology - MTech, Computer Science, Indian Institute of Technology, Delhi
· Doctor of Philosophy - PhD, Machine Learning, University of Oxford

Publications (29)

MAVEN: Multi-Agent Variational Exploration
Neural Information Processing Systems · 2019
408
cited
RODE: Learning Roles to Decompose Multi-Agent Tasks
International Conference on Learning Representations · 2020
259
cited
Open-Ended Learning Leads to Generally Capable Agents
arXiv.org · 2021
220
cited
SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Neural Information Processing Systems · 2022
136
cited
Mining Financial News for Major Events and Their Impacts on the Market
2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology · 2008
63
cited
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
International Conference on Machine Learning · 2020
59
cited
VIREL: A Variational Inference Framework for Reinforcement Learning
Neural Information Processing Systems · 2018
58
cited
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning
International Conference on Machine Learning · 2021
38
cited
Symmetry Learning for Function Approximation in Reinforcement Learning
arXiv.org · 2017
31
cited
Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
Neural Information Processing Systems · 2024
28
cited
Generalization in Cooperative Multi-Agent Systems
arXiv.org · 2022
24
cited
Feature Selection for Short Text Classification using Wavelet Packet Transform
Conference on Computational Natural Language Learning · 2015
13
cited
Document Clustering for Event Identification and Trend Analysis in Market News
2009 Seventh International Conference on Advances in Pattern Recognition · 2009
12
cited
SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching
arXiv.org · 2021
12
cited
Effects of Spectral Normalization in Multi-Agent Reinforcement Learning
IEEE International Joint Conference on Neural Network · 2022
11
cited
Symmetry Detection and Exploitation for Function Approximation in Deep RL
Adaptive Agents and Multi-Agent Systems · 2017
11
cited
Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
arXiv.org · 2021
9
cited
Suggestive Approaches to Create a Recommender System for GitHub
2017
9
cited
Model based Multi-agent Reinforcement Learning with Tensor Decompositions
arXiv.org · 2021
8
cited
From Interaction to Impact: Towards Safer AI Agent Through Understanding and Evaluating Mobile UI Operation Impacts
International Conference on Intelligent User Interfaces · 2024
7
cited
Sotabase
Anuj Mahajan | Researcher Profile | Sotabase | Sotabase