Research

clustering player paths
Jonathan Campbell, Jonathan Tremblay, Clark VerbruggeFDG'15
exploration in NetHack using occupancy maps
Jonathan Campbell, Clark VerbruggeFDG'17
learning combat in NetHack
Jonathan Campbell, Clark VerbruggeAIIDE'17
exploration in NetHack with secret discovery
Jonathan Campbell, Clark VerbruggeIEEE TOG (arXiv)
  • Jonathan Campbell, Jonathan Tremblay, Clark Verbrugge. "Clustering Player Paths." FDG'15: Proceedings of the 10th International Conference on the Foundations of Digital Games. Monterey, California. June 2015. official site paper bibtex
  • Jonathan Campbell, Clark Verbrugge. "Exploration in NetHack Using Occupancy Maps." FDG'17: Proceedings of the 12th International Conference on the Foundations of Digital Games. Hyannis, Massachusetts. August 2017. pp.42:1–42:4. official site paper bibtex
  • Jonathan Campbell, Clark Verbrugge. "Learning Combat in NetHack." AIIDE'17: Proceedings of the 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. Snowbird City, Utah. October 2017. pp.16–22. official site paper bibtex
  • Jonathan Campbell, Clark Verbrugge. "Exploration in NetHack With Secret Discovery." in IEEE Transactions on Games. 2018. To appear in a future issue. official site paper bibtex

Implementations

procedural sokoban generator
based on Taylor & Parberry's paper
NethackRL

coming late 2018OpenAI Gym

Thesis

exploration & combat in NetHack

M.Sc. Thesis

Sometimes you don't understand because of the language, say the fella comes from America and he talks too fast. That's my fault and I apologize, that's a kind of trivial difficulty, relatively. Next kind of not understanding is because we perhaps use new words. Again, my job. Then there's a kind of saying you don't understand it meaning, 'I don't believe it, it's too crazy, it's the kind of thing I'm just not going to accept.' This kind, I hope you'll come along with me, and you'll have to accept it, because it's the way nature works. If you want to know the way nature works, we looked at it carefully, and that's the way it looks. You don't like it? Go somewhere else! To another universe, where the rules are simpler, philosophically more pleasing, more psychologically easy. I can't help it, okay?

Richard Feynman, QED: Photons - Corpuscles of Light (Sir Douglas Robb Lectures, 1979)