def test_view(self):
g = nx.Graph()
g.add_edges_from([(0, 1), (1, 2), (2, 3), (3, 4), (1, 5)])
nx.set_node_attributes(g, {
0: (0, 1),
1: (0, 2),
2: (0, 3),
3: (0, 4),
4: (0, 5),
5: (1, 1)
},
name="coords")
orders = [(3, 2, 2, 3, 3)
] # <source, destination, time, length, price>
drivers = np.array([1, 1, 1, 1, 1, 1])
action = np.array([1, 0, 0], dtype=float)
env = TaxiEnv(g, orders, 1, drivers, 10)
env.seed(123)
env.set_view([2, 3, 4])
obs, _, _ = env.get_observation()
# check observation space and content
assert env.observation_space_shape == obs.shape
view_size = 3
assert env.observation_space_shape == (
view_size * 4 + 10,
) # default income is not included, so its <driver, order, idle, time_id, node_id>
assert env.action_space_shape == (
3,
) # degree of 1 is 3, but of the rest is 2. So it should be 2 + 1 (staying action)
assert env.current_node_id in [2, 3, 4]
# an action [1, 0, 0] for the node 2 means to go to node 3, because its the only neighbor in the view
env.step(action)
assert env.current_node_id in [2, 3, 4]
env.step(action)
assert env.current_node_id in [2, 3, 4]
obs, rew, done, info = env.step(action)
assert (obs[:view_size] == np.array([0.5, 1, 0])).all(
) # there are 2 drivers in the node 3 at the end, one from node 2, one from node 4.
assert (obs[view_size:2 * view_size] == np.array([0, 0, 0])).all()
assert (obs[2 * view_size:3 * view_size] == np.array([0.5, 1,
0])).all()
# next time iteration should happen
assert env.time == 1
assert env.current_node_id in [2, 3]
assert (obs[2 * view_size:3 * view_size] == np.array([0.5, 1,
0])).all()
assert (obs[3 * view_size:3 * view_size + 10] == np.array(
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0])).all()
assert obs[3 * view_size + 10:].shape == (3, )
assert (obs[3 * view_size + 10:] == np.array([
1, 0, 0
])).all() or (obs[3 * view_size + 10:] == np.array([0, 1, 0])).all()
assert [d.position for d in env.all_driver_list] == [0, 1, 3, 2, 3, 5]
def test_sync(self):
g = nx.Graph()
g.add_edges_from([(0, 1), (1, 2), (2, 3)])
nx.set_node_attributes(g, {
0: (0, 1),
1: (0, 2),
2: (1, 1),
3: (1, 2)
},
name="coords")
orders = [(0, 1, 0, 1, 1), (1, 1, 1, 2, 2), (2, 2, 1, 3, 3),
(3, 2, 2, 3, 3)]
drivers = np.array([1, 0, 0, 5])
action = np.array([0.3, 0.4, 0.3], dtype=float)
env = TaxiEnv(g, orders, 1, drivers, 10)
env.step(action)
env2 = TaxiEnv(g, orders, 1, drivers, 10)
env2.sync(env)
o1, _, _ = env.get_observation()
o2, _, _ = env2.get_observation()
assert (o1 == o2).all()
env.seed(1)
env2.seed(1)
while not env.done:
obs, rew, done, info = env.step(action)
obs2, rew2, done2, info2 = env2.step(action)
assert (obs == obs2).all()
assert rew == rew2
assert done == done2
assert info == info2