Hi, I am Abdus Salam Azad, a Ph.D. student at UC Berkeley. I am fortunate enough to be advised by Prof. Ion Stoica. I also collaborate with Prof. Pieter Abbeel from UC Berkeley and Izzeddin Gür & Aleksandra Faust from Google Brain. My research interest lies broadly in Reinforcement Learning: particularly representation learning for Curriculum Learning, Environment & Data Generation for RL, and Unsupervised RL.
I have also worked on Program Analysis for Auto-Parallelizing Python Programs and Genetic Algorithms to solve complex real-world Combinatorial Optimization problems. I completed my Bachelor of Science in July 2014 and Masters of Science in January 2017 from CSE, BUET. You can find my CV here (updated December 2021).
Selected Publications (C: conference / J: journal / P: preprint *: equal contributions)
[P] CLUTR: Curriculum Learning via Unsupervised Task Representation Learning [arxiv]
[C] Programmatic Modeling and Generation of Real-time Strategic Soccer Environments for Reinforcement Learning [preprint]
[J] A Heuristic Initialized Stochastic Memetic Algorithm for MDPVRP With Interdependent Depot Operations [pdf]
Abdus Salam Azad; Monirul Islam; Saikat Chakraborty