Craig Innes


I did an undergraduate masters in Informatics (MInf) at the University of Edinburgh, worked as a programmer for a bit, then changed my mind and went back to University. I did my PhD at the Institute for Language, Cognition and Computation at Edinburgh, and am currently working as a Post-Doctorate research associate one building over in the Institute for Perception, Action, and Behaviour.


My PhD thesis was all about Unawareness: What happens when computational agents have to learn the task itself as they go along (rather than just optimizing parameters in a pre-specified domain)?

In my current role, I'm interested in incorporating safety guarantees and interpretability properties into robotic and computer vision tasks.


Conference Papers

  • Innes, C., & Ramamoorthy, S. (2020). Elaborating on Learned Demonstrations with Temporal Logic Specifications. In Robotics Science and Systems
  • Innes, C., & Lascarides, A. (2019). Learning Factored Markov Decision Processes with Unawareness. In Uncertainty in Artificial Intelligence
  • Innes, C., & Lascarides, A. (2019). Learning Structured Decision Problems with Unawareness. In International Conference on Machine Learning

Extended Abstracts

  • Innes, C., & Lascarides, A. (2019). Learning Factored Markov Decision Processes with Unawareness - Extended Abstract. In International Conference on Autonomous Agents and Multiagent Systems


In my spare time I like to design small games. You can find a list of them on my page. If you're interested in making games, I suggest using Unity, or GameMaker , then joining a Game Jam to get inspired.


You can email me at [my-first-name] [dot] [my-last-name] [at] ed [dot] ac [dot] uk