Abhishek Naik

Abhishek Naik

Founding Member of Technical Staff · Oak Lab

Ph.D., University of Alberta & Amii

I am a Founding Member of Technical Staff at Oak Lab, where we are building algorithms that will enable all kinds of artificial systems to learn continually in real time—from their own experience—with orders of magnitude less compute and energy than contemporary methods.

Recently, I finished a postdoc at the National Research Council Canada, where I did reinforcement-learning research at the intersection of robotics and space applications. Check out this video of our robot dog (Rocky!) traversing lunar-like terrain zero-shot after learning to walk purely in simulation in less than 20 minutes using a single GPU!

Previously, I obtained my Ph.D. at the University of Alberta with Rich Sutton, where I developed simple and practical algorithms from first principles for long-lived artificial decision-making systems. In particular, I developed algorithms within the reinforcement-learning framework for continuing (non-episodic) problems—in which the agent-environment interaction goes on ad infinitum—with the goal of maximizing the average reward obtained per step. Empirically, the algorithms are easy to implement and use.

I love space! I envision a future where artificial systems will have human-like intelligence and adaptability, making space exploration significantly easier and safer for our species.

Updates

Ph.D. Dissertation

    Selected Papers Google Scholar ↗

      Selected Talks

      Background

      Interests & Hobbies

        Contact

        Feel free to reach out via abhisheknaik22296@gmail.com or connect on LinkedIn.

        Recent Writing

        All Posts ↗