Skip to content

shehio/monte-carlo-tree-search

Repository files navigation

Monte Carlo Tree Search

This repo provides an implementation for MCTS algorithm. We provide a solid interface for other perfect-information games too. Although, we believe that for the rollout, domain-specific heuristics could be more useful.

Change the logger level in main.py to DEBUG so that you learn more about how the algorithm works.

MCTS came into prominence after DeepMind's AlphaGo utilized it to beat Lee Sedol, Go's world champion at the time.

Resources

TODOS

  • Add mypy to the build pipeline
  • Provide Unit tests, Tox, and Travis
  • Add Connect 4 and other simple games
  • Add NNs: CNNs and RESNET rather than the rollout strategy
  • Create a chess-playing api executing this code on AWS Lambda or Azure Functions

Releases

No releases published

Packages

No packages published

Languages