I am currently working within BAIR and CHAI, collaborating with Anca Dragan, Rohin Shah, and Jakob Foerster on developing frameworks for better collaboration between AI agents and humans.

I am also involved with Ken Goldberg on an AI art exhibition that will take place in Spring 2020. In the past I’ve worked with Yun Song on population genetics.

My long term objective is to help reduce the risks associated with the use of new technologies, in particular ones related to AI and the Value Alignment problem.

Conference Papers

  • On the Utility of Learning about Humans for Human-AI Coordination. Micah Carroll, Rohin Shah, Mark Ho, Tom Griffiths, Sanjit Seshia, Pieter Abbeel, Anca Dragan. NeurIPS 2019.
    [paper] [environment] [code] [blogpost coming soon]
  • Workshop Papers and Other Writing

  • On the Utility of Learning about Humans for Human-AI Coordination. Micah Carroll, Rohin Shah, Mark Ho, Tom Griffiths, Sanjit Seshia, Pieter Abbeel, Anca Dragan. Imitation, Intent, and Interaction Workshop, ICML 2019. [paper] [code] [poster]
  • Overview of Current AI Alignment Approaches. Micah Carroll. Final Project for AI Safety and Control (CS294-149 at UC Berkeley), 2018. [paper]
  • Learning

  • Machine Learning and Convex Optimization Class Notes
  • Sutton & Barto - Reinforcement Learning: Some Notes and Exercises
  • Teaching

  • Summer 2018 - CS 188 Discussion Section