Sotabase

Career

· Senior Research Scientist, Microsoft Research2025–
· Senior Research Consultant, SDAIA2024–2025
· Research Scientist, DreamFold AI2023–2024
· Research Intern, Morgan Stanley2023–2023
· Research Intern, Apple MLR2022–2022
· Research Intern, Microsoft Research2022–2023
· Research Intern, Microsoft Research NYC2021–2021
· Research Intern, Borealis AI2020–2021
· Research Intern, Microsoft Research Montreal2018–2019
· PhD Student, McGill University2017–2022
· Research Intern, Microsoft Research Montreal2017–2017
· MPhil, University of Cambridge2016–2017
· Research Intern, Caltech Surf Program2015–2015
· Research Intern, Johns Hopkins SRE Program2014–2014
· Industrial Placement Intern, J.P. Morgan2013–2014
· Intern, Deutsche Bank2012–2012
· Undergraduate, University College London, UCL2011–2015

Publications (91)

Deep Reinforcement Learning that Matters
AAAI Conference on Artificial Intelligence · 2017
2,173
cited
Deep Bayesian Active Learning with Image Data
International Conference on Machine Learning · 2017
1,892
cited
An Introduction to Deep Reinforcement Learning
Found. Trends Mach. Learn. · 2018
1,419
cited
Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
arXiv.org · 2017
275
cited
InfoBot: Transfer and Exploration via the Information Bottleneck
International Conference on Learning Representations · 2019
176
cited
Bayesian Hypernetworks
arXiv.org · 2017
145
cited
Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
Trans. Mach. Learn. Res. · 2022
33
cited
RE-EVALUATE: Reproducibility in Evaluating Reinforcement Learning Algorithms
2018
29
cited
Alzheimer's Disease and Dementia Detection from 3D Brain MRI Data Using Deep Convolutional Neural Networks
2018 3rd International Conference for Convergence in Technology (I2CT) · 2018
28
cited
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
arXiv.org · 2022
21
cited
Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
arXiv.org · 2022
21
cited
Marginalized State Distribution Entropy Regularization in Policy Optimization
arXiv.org · 2019
19
cited
Exploring Restart Distributions.
2020
14
cited
Bayesian Policy Gradients via Alpha Divergence Dropout Inference
arXiv.org · 2017
13
cited
Ignorance is Bliss: Robust Control via Information Gating
Neural Information Processing Systems · 2023
13
cited
Behavior Prior Representation learning for Offline Reinforcement Learning
International Conference on Learning Representations · 2022
12
cited
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
arXiv.org · 2022
12
cited
Learning Latent Dynamic Robust Representations for World Models
International Conference on Machine Learning · 2024
12
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
Sotabase
Riashat Islam | Researcher Profile | Sotabase | Sotabase