Skip to content

Repository files navigation

Wappo game in Reinforcement Learning application

Rules of the game:

  • Player (blue rhombus): takes one step per round
  • Monster (red x): takes two steps per round; always takes the shortest route towards the player; always moves horizontally first, if no longer possible vertically
  • Pentagram (orange star in cercle): monster is frozen for 3 rounds; to be frozen again, monster must re-enter the pentagram
  • Goal (green house): player should reach house

alt text

Example

python run_wappo_level.py 142

level_142_demo.mp4

References

  • Rich Sutton and Andrew Barto. Reinforcement Learning: An Introduction, Second Edition, 2016.

About

Reinforcement learning project for Wappo game

Topics

Resources

Stars

1 star

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages