Hi, I am Abdus Salam Azad, a final year Ph.D. student at UC Berkeley (expected graduation December 2024). 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 is funded by Google. Inc. & BAIR Commons Research initiative.
My research interest lies broadly in Reinforcement Learning: Representation Learning for Curriculum Learning, Environment Generation for RL, and LLM based RL agents.
Previously, I have also worked on 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 resume here.
Thanks for visiting my site. Have a good day.
Selected Publications (C: conference / J: journal / P: preprint *: equal contributions)
[P] CLUTR: Curriculum Learning via Unsupervised Task Representation Learning [arxiv]
Abdus Salam Azad, Izzeddin Gur, Aleksandra Faust, Pieter Abbeel, Ion Stoica
International Conference on Machine Learning (ICML) 2023
[C] Programmatic Modeling and Generation of Real-time Strategic Soccer Environments for Reinforcement Learning [preprint]
Abdus Salam Azad*, Edward Kim*, Qiancheng Wu, Kimin Lee, Alberto Sangiovanni-Vincentelli, Ion Stoica, Pieter Abbeel, Sanjit A. Seshia
[J] A Heuristic Initialized Stochastic Memetic Algorithm for MDPVRP With Interdependent Depot Operations [pdf]
Abdus Salam Azad; Monirul Islam; Saikat Chakraborty