def run_task(*_): """Implement the run_task method needed to run experiments with rllab.""" sim_params = SumoParams(sim_step=0.1, render=False) vehicles = VehicleParams() vehicles.add(veh_id="rl", acceleration_controller=(RLController, {}), routing_controller=(ContinuousRouter, {}), num_vehicles=1) vehicles.add(veh_id="human", acceleration_controller=(IDMController, {}), routing_controller=(ContinuousRouter, {}), num_vehicles=21) additional_env_params = { "ring_length": [220, 270], "max_accel": 1, "max_decel": 1 } env_params = EnvParams(horizon=HORIZON, additional_params=additional_env_params, warmup_steps=750) additional_net_params = { "length": 260, "lanes": 1, "speed_limit": 30, "resolution": 40 } net_params = NetParams(additional_params=additional_net_params) initial_config = InitialConfig(spacing="uniform", bunching=50) scenario = LoopScenario(exp_tag, vehicles, net_params, initial_config=initial_config) env_name = "WaveAttenuationPOEnv" pass_params = (env_name, sim_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=(3, 3), ) baseline = LinearFeatureBaseline(env_spec=env.spec) algo = TRPO( env=env, policy=policy, baseline=baseline, batch_size=60000, max_path_length=horizon, n_itr=500, # whole_paths=True, discount=0.999, # step_size=v["step_size"], ) algo.train(),
def ring_road_exp_setup(sim_params=None, vehicles=None, env_params=None, net_params=None, initial_config=None, traffic_lights=None): """ Create an environment and scenario pair for ring road test experiments. Parameters ---------- sim_params : flow.core.params.SumoParams sumo-related configuration parameters, defaults to a time step of 0.1s and no sumo-imposed failsafe on human or rl vehicles vehicles : Vehicles type vehicles to be placed in the network, default is one vehicles with an IDM acceleration controller and ContinuousRouter routing controller. env_params : flow.core.params.EnvParams environment-specific parameters, defaults to a environment with no failsafes, where other parameters do not matter for non-rl runs net_params : flow.core.params.NetParams network-specific configuration parameters, defaults to a single lane ring road of length 230 m initial_config : flow.core.params.InitialConfig specifies starting positions of vehicles, defaults to evenly distributed vehicles across the length of the network traffic_lights : flow.core.params.TrafficLightParams traffic light signals, defaults to no traffic lights in the network """ logging.basicConfig(level=logging.WARNING) if sim_params is None: # set default sim_params configuration sim_params = SumoParams(sim_step=0.1, render=False) if vehicles is None: # set default vehicles configuration vehicles = VehicleParams() vehicles.add(veh_id="idm", acceleration_controller=(IDMController, {}), routing_controller=(ContinuousRouter, {}), car_following_params=SumoCarFollowingParams( speed_mode="aggressive", ), num_vehicles=1) if env_params is None: # set default env_params configuration additional_env_params = { "target_velocity": 8, "max_accel": 1, "max_decel": 1, "sort_vehicles": False, } env_params = EnvParams(additional_params=additional_env_params) if net_params is None: # set default net_params configuration additional_net_params = { "length": 230, "lanes": 1, "speed_limit": 30, "resolution": 40 } net_params = NetParams(additional_params=additional_net_params) if initial_config is None: # set default initial_config configuration initial_config = InitialConfig(lanes_distribution=1) if traffic_lights is None: # set default to no traffic lights traffic_lights = TrafficLightParams() # create the scenario scenario = LoopScenario(name="RingRoadTest", vehicles=vehicles, net_params=net_params, initial_config=initial_config, traffic_lights=traffic_lights) # create the environment env = AccelEnv(env_params=env_params, sim_params=sim_params, scenario=scenario) # reset the environment env.reset() return env, scenario