Usman Anwar

I am a PhD student in Computational and Biological Learning lab at Cambridge University, UK. I am interested in reinforcement learning, multi-agent learning and AI Safety. I am supervised by David Kruger and funded by Open Phil AI Fellowship and Vitalik Buterin Fellowship on AI Safety. Previously, I was a MS student at the Information Technology University, Pakistan, where I graduated second in my class and was awarded Graduate Student Fellowship.

Email  /  GitHub  /  Google Scholar  /  LinkedIn  /  CV

If you want to chat with me, please get in touch here.

xyz1 photo

Publications (Check google scholar - this is out of date!)

project1 image

Inverse Constrained Reinforcement Learning


Usman Anwar, Shehryar Malik, Alireza Aghasi, Ali Ahmed
Internation Conference on Machine Learning, 2021
arxiv / video / code / poster / slides /

We propose a framework for learning Markovian constraints from user demonstrations in high dimensional, continuous settings. We empirically show that constraints thus learned are general and transfer well to agents with different dynamics and morphologies.

[Workshops]

project1 image

Bayesian Inverse Constrained Reinforcement Learning


Dimitris Papadimitriou, Usman Anwar, Daniel Brown
NeurIPS 2021 Workshop on Safe and Robust Control of Uncertain Systems, 2021
paper / poster /

We develop a Bayesian approach for learning constraints which provides several advantages as it can work with partial trajectories, is applicable in both stochastic and deterministic environments and due to its ability to provide a posterior distribution enables use of active learning for accurate learning of constraints.

project1 image

Learning To Solve Differential Equations Across Initial Conditions


Usman Anwar, Shehryar Malik, Alireza Aghasi, Ali Ahmed
DeepDiffEq Workshop at ICLR, 2020
arxiv / slides /

We extend the PINN’s framework for finding the solution of a Partial Differential Equation to work across initial conditions by casting the problem as a generative model and using an info-GAN like architecture.


Notes

These include notes on different topics in topics relevant to machine learning.

  • Notes on advanced convex optimization. Covers analysis of sub-gradient method, projected gradient method, proximal gradient method and mirror descent. These notes are work in progress and will be updated with new material.


Design and source code from Leonid Keselman's website