from debug_log import DebugLog
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("-m", "--model_path")
args = parser.parse_args()
env = CatchBall()
agent = DQNAgent(env.enable_actions, env.name)
agent.load_model(args.model_path)
env.reset_board_status()
env.set_test_game()
# 1ゲーム内の処理開始地点
while env.is_playable() is True:
env.print_board()
env.test_player_play()
state = env.observe()
while True is True:
action = agent.select_action(state, 0.0)
hand_result = env.test_ai_play(action)
if hand_result == "ok":
break
elif hand_result == "ng":
x = int(action % 8)
y = int(action / 8)
DebugLog.error(str(action) + ":" + str(x) + ":" + str(y))
pass
env = CatchBall()
agent = DQNAgent(env.enable_actions, env.name)
total_result_log = ""
for e in range(n_game):
# るーぷ開始地点
frame = 0
win = 0
loss = 0.0
Q_max = 0.0
env.reset_board_status()
env.set_new_game()
state_after = env.observe()
# 1ゲーム内の処理開始地点
while env.is_playable() is True:
# print "*********************************************************************************"
state_before = copy.deepcopy(state_after)
# 自分の手がOKになるまでループ（置けないところに置く可能性がある為）
while True is True:
env.is_available()
# 手を選ばせる。盤面情報と手のブレ率（random)を与える
# hand_result = env.random_play()
action_t = agent.select_action(state_before, agent.exploration)
hand_result = env.learning_play(action_t)
if hand_result == "ok":
break
