StateOfThreeGenerator(world, i, ["state_of_three"], in_only=True, average=None),
LaneVehicleGenerator(world, i, ["lane_waiting_count"], in_only=True, average="all", negative=True),
i,
world,
file_name,
info_file
))
if args.load_model:
agents[-1].load_model(args.save_dir)
print(i.phases)
# Create metric
metric = [TravelTimeMetric(world), ThroughputMetric(world), SpeedScoreMetric(world), MaxWaitingTimeMetric(world)]
# create env
env = TSCEnv(world, agents, metric)
#
n_agents = len(agents)
# train dqn_agent
def train(args, env):
for e in range(episodes):
for agent in agents: agent.reset_episode_infos()
first_obs = np.array(env.reset())*0.01
current_obs = first_obs
'red_v': args.red_v
}
#Create world
world = World(args.config_file, thread_num=args.thread)
#Create agents
agents = []
for i in world.intersections:
action_space = gym.spaces.Discrete(len(i.phases))
agents.append(SOTLAgent(action_space, options, i, world))
# Create metric
metric = [
TravelTimeMetric(world),
ThroughputMetric(world),
SpeedScoreMetric(world),
MaxWaitingTimeMetric(world)
]
#Create env
env = TSCEnv(world, agents, metric)
obs = env.reset()
actions = []
steps = 0
episodes_rewards = 0
#Walk through the steps
while steps < args.steps:
type=int,
default=1,
help='how often agent make decisions')
args = parser.parse_args()
# create world
world = World(args.config_file, thread_num=args.thread)
# create agents
agents = []
for i in world.intersections:
action_space = gym.spaces.Discrete(len(i.phases))
agents.append(SOTLAgent(action_space, i, world))
# create metric
metric = ThroughputMetric(world)
# create env
env = TSCEnv(world, agents, metric)
def test(met, met_name):
# simulate
obs = env.reset()
env.update_metric(met)
actions = []
for i in range(args.steps):
actions = []
for agent_id, agent in enumerate(agents):
actions.append(agent.get_action(obs[agent_id]))