sensor = world.get_sensor_info() f = [0]*len(sensor) for i in range(len(sensor)): f[i] = sensor[i] #Choose Bots bot_RL = Bot_RL_MLP(size_x, size_y, rl_beta, mlp_hidden, mlp_learning_rate, rl_reward, initial_field = f, player_ID = 1) bot_train = Bot_Random.Bot_Random_Static(size_x, size_y) #bot_train = Bot_Random.Bot_Random_Dynamic(size_x, size_y) win = [[],[],[]] scale = [] winner = [0,0,0] for counter in range (runs): bot_RL.play_game(world, 1, bot_train) #bot_1.new_game() #bot_2.new_game() #Play a game #Make a move until Game ends #world.new_init(initial_stones = initial_stones) #while (world.get_winner() == -1): # if (world.active_player == 1): # (x, y) = bot_1.get_action(world) # world.perform_action(x, y) # bot_1.evaluate_action(world) # else: # (x, y) = bot_2.get_action(world) # world.perform_action(x, y) # bot_2.evaluate_action(world)