Generative Sequence Models for Sequential Decision Making
Aditya Grover is an Assistant Professor of Computer Science at UCLA. His goal is to develop efficient machine learning approaches for probabilistic reasoning under limited supervision, with a focus on deep generative modeling and sequential decision-making under uncertainty. He is also an affiliate faculty at the UCLA Institute of the Environment and Sustainability, where he grounds his research in real-world applications in climate science and sustainable energy. His 35+ research works have been published at top-tier scientific conferences and journals including Nature, deployed into production at major technology companies (Instagram, Twitter), and covered in major press venues, such as the Wall Street Journal and Wired. Aditya’s research has been recognized with two best paper awards (NeurIPS, StarAI), several research fellowships (Google-Simons Institute, Microsoft Research, Lieberman, Adobe), and the ACM SIGKDD doctoral dissertation award. Aditya received his postdoctoral training at UC Berkeley, Ph.D. from Stanford, and bachelors from IIT Delhi, all in computer science.
The ability to make decisions under uncertainty is a key component of intelligence. We introduce a framework that abstracts sequential decision making as a generative sequence modeling problem. This allows us to draw upon the simplicity and scalability of the Transformer architecture, and associated advances in language modeling such as GPT-x. I will show how this framework permits learning from large offline datasets, uncertainty-guided online exploration, and generalization across multiple tasks. On various benchmarks from continuous control to game playing, our framework matches or exceeds the performance of state-of-the-art algorithms.
Related seminars
Stony Brook University
Washington State University
University of Melbourne
National University of Singapore