def setUp(self):
vehicles = VehicleParams()
vehicles.add("rl", acceleration_controller=(RLController, {}))
vehicles.add("human", acceleration_controller=(IDMController, {}))
self.sim_params = SumoParams()
self.scenario = TwoLoopsOneMergingScenario(
name="test_merge",
vehicles=vehicles,
net_params=NetParams(
no_internal_links=False,
additional_params=LM_PARAMS.copy(),
),
)
self.env_params = EnvParams(
additional_params={
"max_accel": 3,
"max_decel": 3,
"target_velocity": 10,
"n_preceding": 2,
"n_following": 2,
"n_merging_in": 2,
"sort_vehicles": True
}
)
def loop_merge_example(render=None):
"""
Perform a simulation of vehicles on a loop merge.
Parameters
----------
render : bool, optional
specifies whether to use sumo's gui during execution
Returns
-------
exp: flow.core.SumoExperiment type
A non-rl experiment demonstrating the performance of human-driven
vehicles on a loop merge.
"""
sumo_params = SumoParams(sim_step=0.1,
emission_path="./data/",
render=True)
if render is not None:
sumo_params.render = render
# note that the vehicles are added sequentially by the scenario,
# so place the merging vehicles after the vehicles in the ring
vehicles = Vehicles()
vehicles.add(veh_id="idm",
acceleration_controller=(IDMController, {}),
lane_change_controller=(SumoLaneChangeController, {}),
routing_controller=(ContinuousRouter, {}),
num_vehicles=7,
speed_mode="no_collide",
sumo_car_following_params=SumoCarFollowingParams(minGap=0.0,
tau=0.5),
sumo_lc_params=SumoLaneChangeParams())
vehicles.add(veh_id="merge-idm",
acceleration_controller=(IDMController, {}),
lane_change_controller=(SumoLaneChangeController, {}),
routing_controller=(ContinuousRouter, {}),
num_vehicles=10,
speed_mode="no_collide",
sumo_car_following_params=SumoCarFollowingParams(minGap=0.01,
tau=0.5),
sumo_lc_params=SumoLaneChangeParams())
env_params = EnvParams(additional_params=ADDITIONAL_ENV_PARAMS)
additional_net_params = ADDITIONAL_NET_PARAMS.copy()
additional_net_params["ring_radius"] = 50
additional_net_params["inner_lanes"] = 1
additional_net_params["outer_lanes"] = 1
additional_net_params["lane_length"] = 75
net_params = NetParams(no_internal_links=False,
additional_params=additional_net_params)
initial_config = InitialConfig(x0=50,
spacing="uniform",
additional_params={"merge_bunching": 0})
scenario = TwoLoopsOneMergingScenario(name="two-loop-one-merging",
vehicles=vehicles,
net_params=net_params,
initial_config=initial_config)
env = AccelEnv(env_params, sumo_params, scenario)
return SumoExperiment(env, scenario)
def run_task(*_):
"""Implement the run_task method needed to run experiments with rllab."""
sumo_params = SumoParams(sim_step=0.2, render=True)
# note that the vehicles are added sequentially by the scenario,
# so place the merging vehicles after the vehicles in the ring
vehicles = Vehicles()
# Inner ring vehicles
vehicles.add(veh_id="human",
acceleration_controller=(IDMController, {
"noise": 0.2
}),
lane_change_controller=(SumoLaneChangeController, {}),
routing_controller=(ContinuousRouter, {}),
num_vehicles=6,
sumo_car_following_params=SumoCarFollowingParams(minGap=0.0,
tau=0.5),
sumo_lc_params=SumoLaneChangeParams())
# A single learning agent in the inner ring
vehicles.add(veh_id="rl",
acceleration_controller=(RLController, {}),
lane_change_controller=(SumoLaneChangeController, {}),
routing_controller=(ContinuousRouter, {}),
num_vehicles=1,
sumo_car_following_params=SumoCarFollowingParams(
minGap=0.01, tau=0.5, speed_mode="no_collide"),
sumo_lc_params=SumoLaneChangeParams())
# Outer ring vehicles
vehicles.add(veh_id="merge-human",
acceleration_controller=(IDMController, {
"noise": 0.2
}),
lane_change_controller=(SumoLaneChangeController, {}),
routing_controller=(ContinuousRouter, {}),
num_vehicles=10,
sumo_car_following_params=SumoCarFollowingParams(minGap=0.0,
tau=0.5),
sumo_lc_params=SumoLaneChangeParams())
env_params = EnvParams(horizon=HORIZON,
additional_params={
"max_accel": 3,
"max_decel": 3,
"target_velocity": 10,
"n_preceding": 2,
"n_following": 2,
"n_merging_in": 2,
})
additional_net_params = ADDITIONAL_NET_PARAMS.copy()
additional_net_params["ring_radius"] = 50
additional_net_params["inner_lanes"] = 1
additional_net_params["outer_lanes"] = 1
additional_net_params["lane_length"] = 75
net_params = NetParams(no_internal_links=False,
additional_params=additional_net_params)
initial_config = InitialConfig(x0=50,
spacing="uniform",
additional_params={"merge_bunching": 0})
scenario = TwoLoopsOneMergingScenario(name=exp_tag,
vehicles=vehicles,
net_params=net_params,
initial_config=initial_config)
env_name = "TwoLoopsMergePOEnv"
pass_params = (env_name, sumo_params, vehicles, env_params, net_params,
initial_config, scenario)
env = GymEnv(env_name, record_video=False, register_params=pass_params)
horizon = env.horizon
env = normalize(env)
policy = GaussianMLPPolicy(env_spec=env.spec, hidden_sizes=(100, 50, 25))
baseline = LinearFeatureBaseline(env_spec=env.spec)
algo = TRPO(
env=env,
policy=policy,
baseline=baseline,
batch_size=64 * 3 * horizon,
max_path_length=horizon,
# whole_paths=True,
n_itr=1000,
discount=0.999,
# step_size=0.01,
)
algo.train()