/chainreaction_sanchi

Game I am building to learn reinforcement learning

Primary LanguagePython

Rule

  1. The gameplay takes place in an m * n board. The most commonly used size of the board is 9 * 6.
  2. For each cell in the board, we define a critical mass. The critical mass is equal to the number of orthogonally adjacent cells. That would be 4 for usual cells, 3 for cells in the edge and 2 for cells in the corner.
  3. All cells are initially empty. The red and the green player takes turns to place "orbs" of their corresponding colors. The Red player can only place an