Pulkit Agrawal

Pulkit Agrawal is the Steven and Renee Finn Career Development Professor, Assistant Professor.assistant professor in MIT’s Department of Electrical Engineering and Computer Science. His research interests span robotics, deep learning, computer vision and reinforcement learning. Agrawal’s overarching goal is to build machines that can automatically and continuously learn about their environment to reach what humans consider common sense. Agrawal earned his BS from IIT Kanpur and was awarded the Director’s Gold Medal. He earned his PhD from UC Berkeley and co-founded SafelyYou Inc. His work has appeared in MIT Tech Review, Quanta and New Scientist. He is a recipient of Sony Faculty Research Award, Signatures Fellow Award, Fulbright Science and Technology Award, Goldman Sachs Global Leadership Award, OPJEMS and Sridhar Memorial Prize, among others. Agrawal holds the equivalent of a BA in Indian classical music and occasionally performs.

Selected Publications

• Ajay, A., Du, Y., Gupta, A., Tenenbaum, J., Jaakkola, T., Agrawal, P. (2023) Is conditional generative modeling all you need for decision-making? International Conference on Learning Representations (ICLR).
• Shenfeld, I., Hong, Z.W., Agrawal, P., Tamar, A. (2023) TGRL: Teacher Guided Reinforcement Learning Algorithm for POMDPs. International Conference on Learning Representations (ICLR).
• Ajay, A., Gupta, A., Ghosh, D., Levine, S., Agrawal, P (2022) Distributionally Adaptive Meta Reinforcement Learning. 36th Conference on Neural Information Processing Systems (NeurIPS).

Media

• January 9, 2019: MIT News, School of Engineering welcomes new faculty.
• September 19, 2017: Quanta magazine, Clever machines learn how to be curious.
• May 23, 2017: MIT Technology Review, Curiosity may be vital for truly smart AI.

Videos