Ashish Pandian

I am a graduate researcher at the Berkeley Artificial Intelligence Research (BAIR) Lab, where I have the privilege of being advised by Professor Alexandre Bayen. I completed my Bachelor's degree in Mathematics and Computer Science at UC Berkeley. During my undergraduate studies, I was actively involved with the Berkeley Sports Analytics Club and building an autonomous race car with the Formula Electric team.

I am keenly interested in Reinforcement Learning, Control Theory, and Cooperative AI, with a particular emphasis on their applications in everyday robotics. Currently, my research focuses on leveraging deep reinforcement learning to model human driving dynamics, aiming to enhance safe and effective human-AI interactions. Feel free to send me an email if you'd like to chat!

Email  /  Github  /  Twitter  /  Linkedin  /  Scholar

Publications

We introduce Noisy Zero-Shot Coordination (NZSC), where agents train across noisy observations of coordination tasks, enabling robust collaboration with novel partners even without common knowledge of the environment.

Design and source code from Jonathan T. Barron.