everything.study
CMPUT 455

Search, Knowledge and Simulation

3 units

Fall 2021 · Search, Knowledge, and Simulations

Topics

  • Decision-making in humans and machines
  • Heuristic search
  • Game-tree search and pruning
  • Monte Carlo simulation and tree search
  • Feature learning
  • Neural networks
  • Computer Go
  • Reinforcement learning and self-play

Readings

  • Krakovsky. Reinforcement Renaissance.
    required
  • Heingartner. Maybe We Should Leave That Up to the Computer.
    required
  • O’Neil. How Algorithms Rule Our Working Lives.
    required
  • Greenemeyer. 20 Years After Deep Blue. Scientific American, 2017 (author spelling as listed).
    required
  • Schaeffer et al. Checkers Is Solved. Science, 2007.
    required
  • Van der Werf et al. Solving Go on Small Boards.
    required
  • Rémi Coulom. Computing Elo Ratings of Move Patterns in the Game of Go. Computer Games Workshop, Amsterdam, 2007.
    required
  • Browne et al. A Survey of Monte Carlo Tree Search Methods; sections 1–3, 5 and 6.1.9.
    required
  • Pedro Domingos. A Few Useful Things to Know about Machine Learning. Communications of the ACM 55(10), October 2012, pp. 78–87.
    required
  • Maddison, Huang, Sutskever and Silver. Move Evaluation in Go Using Deep Convolutional Neural Networks. CoRR abs/1412.6564.
    required
  • Clark and Storkey. Training Deep Convolutional Neural Networks to Play Go. ICML, 2015.
    recommended
  • Silver, Huang et al. Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature 529, 484–489, 28 January 2016.
    required
  • Silver, Schrittwieser et al. Mastering the Game of Go without Human Knowledge. Nature 550, 354–359.
    required
  • Silver, Hubert et al. A General Reinforcement Learning Algorithm that Masters Chess, Shogi, and Go through Self-Play.
    required
Sources