zlim = (-10, 10, -10, 10)
for i in xrange(0, 1000):
agent.observe()
agent.decide()
agent.act()
agent2.observe()
agent2.decide()
agent2.act()
t = agent.gp.Z[-1].flatten()[-1]
a = [0] * 4
a[0] = agent.gp.Z[-1].flatten()[0]
a[1] = agent.gp.Z[-1].flatten()[1]
a[2] = agent.gp.Z[-1].flatten()[0]
a[3] = agent.gp.Z[-1].flatten()[1]
extent = np.max(np.abs(a))
lim = extent + 3 if extent > 10 else 10
zlim = (-lim, lim, -lim, lim)
fig.clf()
ax1 = fig.add_subplot(1, 3, 1)
ax1.set_aspect('equal')
ax2 = fig.add_subplot(1, 3, 2)
ax2.set_aspect('equal')
ax3 = fig.add_subplot(1, 3, 3)
ax3.set_aspect('equal')
cs = reward.draw(zlim, t, ax1)
agent.draw(zlim, t, ax2, cs)
agent2.draw(zlim, t, ax3, cs)
fig.savefig("./images4/" + str(i).zfill(4) + ".jpg")
