myOrders.append("o %d %d %s\n" % (r, c, d))
enemyOrders = []
enemyAnts = game.player_ants(b)
for i in range(0, len(enemyAnts)):
r = enemyAnts[i].loc[0]
c = enemyAnts[i].loc[1]
d = enemyAction[i]
enemyOrders.append("o %d %d %s\n" % (r, c, d))
game.start_turn()
#print myOrders
game.do_moves(a, myOrders)
#print enemyOrders
game.do_moves(b, enemyOrders)
game.do_orders()
sp = create_map_output(game.map, 0)
# Simulate the battle
(sp, player_ants) = simulate_battle(sp, attackradius2, method)
reward = 0
state = ''.join(s)
newState = ''.join(sp)
sa = state + ''.join(myAction)
if min(player_ants) == 0:
reward = player_ants[0] - player_ants[1]
# Track average reward
