Sreejith Balakrishnan

I am a PhD student at the National University of Singapore, co-supervised by Dr. Bryan Low and Dr. Harold Soh . I am interested in teaching AI agents and robots precisely what to do/achieve to avoid any unexpected consequences. In particular, I design algorithms that enable agents to learn their purpose from watching demonstrations from experts.

Before my PhD, I worked as a Research Engineer at the UNiCEN lab at Singapore Management University (SMU), modelling supply and demand patterns of taxis in Singapore. Before that, I was at ABB Private Limited as a Process Automation Engineer and later as a Section Manager overseeing a team of product specialists in charge of customers from Asia, Australia and New Zealand. For details about my background and research, please take a look at my curriculum vitae and my Google Scholar page.

news

Dec 6, 2022	Reviewing AAMAS 2023 submissions.
Nov 16, 2022	Completed my Thesis Proposal presentation. One step closer to graduation!
Aug 4, 2022	Presenting my thesis under the Student Track at AIES 2022, Oxford.
Aug 1, 2022	Presenting my paper SCALES at AIES 2022, Oxford.
May 14, 2022	Selected for AIES 2022 Student Track in addition to the Main Track. Excited to present my thesis ideas to the scholars at this conference.

selected publications

Efficient exploration of reward functions in inverse reinforcement learning via bayesian optimization

Sreejith Balakrishnan, Quoc Phong Nguyen, Bryan Kian Hsiang Low, and Harold Soh

Advances in Neural Information Processing Systems 2020

Bib

@article{balakrishnan2020efficient,
  title = {Efficient exploration of reward functions in inverse reinforcement learning via bayesian optimization},
  author = {Balakrishnan, Sreejith and Nguyen, Quoc Phong and Low, Bryan Kian Hsiang and Soh, Harold},
  journal = {Advances in Neural Information Processing Systems},
  volume = {33},
  pages = {4187--4198},
  year = {2020},
}

SCALES: From Fairness Principles to Constrained Decision-Making

Sreejith Balakrishnan, Jianxin Bi, and Harold Soh

In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society 2022

Bib

@inproceedings{balakrishnan2022scales,
  title = {SCALES: From Fairness Principles to Constrained Decision-Making},
  author = {Balakrishnan, Sreejith and Bi, Jianxin and Soh, Harold},
  booktitle = {Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society},
  pages = {46--55},
  year = {2022},
}