from game import Checkers
from dqn import DQN
import torch
PATH = "models/30Improve.pt"
dqn = DQN()
dqn.load_state_dict(torch.load(PATH))
game = Checkers()
game.reset()
board = game.board
## Display
print(board)
color = 'red'
while not game.get_game_ended(board, color):
actions = game.get_possible_actions(board, color)
state = game.get_state(board, color)
state_actions = game.make_inputs(state, actions)
if color == 'black':
print("Agent turn")
print("Agent possible actions")
out = dqn(state_actions)
for a, q in zip(actions, out):
print(game.flip_action(a), q.item())
print(torch.max(out))
idx = torch.argmax(out)
action = actions[idx]
class TestBoard(unittest.TestCase):
def setUp(self):
self.test_Game = Checkers()
def test_move(self):
self.test_Game.move((5, 0, 4, 1))
print('move')
expected_result = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, -1, 0, -1, 0, -1],
[0, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
np.testing.assert_array_equal(expected_result,
self.test_Game.board_state)
self.test_Game.reset()
print("capture")
self.test_Game.board_state = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, 0, 0, -1, 0, -1],
[0, 0, -1, 0, -1, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
self.test_Game.move((4, 1, 2, 3))
expected_result = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, 1, 0, -1, 0, -1],
[0, 0, 0, 0, -1, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
np.testing.assert_array_equal(expected_result,
self.test_Game.board_state)
self.test_Game.reset()
print("trying no capture")
self.test_Game.board_state = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, 0, 0, -1, 0, -1],
[0, 0, -1, 0, -1, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
self.test_Game.move((4, 1, 0, 3))
expected_result = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, 0, 0, -1, 0, -1],
[0, 0, -1, 0, -1, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
np.testing.assert_array_equal(expected_result,
self.test_Game.board_state)
self.test_Game.reset()
print("capture from first col")
self.test_Game.turn = -1
self.test_Game.board_state = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, 0, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
self.test_Game.move((3, 0, 5, 2))
expected_result = np.array([[0, -1, 0, -1, 0, -1, 0, -1],
[-1, 0, -1, 0, -1, 0, -1, 0],
[0, -1, 0, 0, 0, -1, 0, -1],
[0, 0, -1, 0, -1, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, -1, 0, 1, 0, 1, 0],
[0, 1, 0, 1, 0, 1, 0, 1],
[1, 0, 1, 0, 1, 0, 1, 0]])
np.testing.assert_array_equal(expected_result,
self.test_Game.board_state)