except ControllerOutOfLaneException:
logger.warning(f"{veh_id} out of lane, skipped attaching sensors")
vehicles_off_road.add(veh_id)
valid_vehicles = {v for v in current_vehicles if v not in vehicles_off_road}
obs, _, _, dones = smarts.observe_from(valid_vehicles)
_record_data(smarts.elapsed_sim_time, obs, collected_data)
# an example of how we might save the data per car
observation_folder = "collected_observations"
if not os.path.exists(observation_folder):
os.makedirs(observation_folder)
for car, data in collected_data.items():
outfile = f"{observation_folder}/{scenario.name}_{scenario.traffic_history.name}_{car}.pkl"
with open(outfile, "wb") as of:
pickle.dump(data, of)
smarts.destroy()
if __name__ == "__main__":
parser = default_argument_parser("observation-collection-example")
args = parser.parse_args()
main(
script=parser.prog,
scenarios=args.scenarios,
headless=args.headless,
seed=args.seed,
)
agent_id, smarts.elapsed_sim_time))
logger.warning(" ... with {}".format(
observations[agent_id].events))
else:
logger.info(
"agent_id={} reached goal @ sim_time={}".
format(agent_id, smarts.elapsed_sim_time))
logger.debug(" ... with {}".format(
observations[agent_id].events))
del observations[agent_id]
smarts.destroy()
if __name__ == "__main__":
parser = default_argument_parser("history-vehicles-replacement-example")
parser.add_argument(
"--replacements-per-episode",
"-k",
help="The number vehicles to randomly replace with agents per episode.",
type=int,
default=1,
)
args = parser.parse_args()
main(
script=parser.prog,
scenarios=args.scenarios,
headless=args.headless,
seed=args.seed,
vehicles_to_replace=args.replacements_per_episode,
for episode in episodes(n=num_episodes):
agent = open_agent_spec.build_agent()
observations = env.reset()
episode.record_scenario(env.scenario_log)
dones = {"__all__": False}
while not dones["__all__"]:
agent_obs = observations[AGENT_ID]
agent_action = agent.act(agent_obs)
observations, rewards, dones, infos = env.step({AGENT_ID: agent_action})
episode.record_step(observations, rewards, dones, infos)
del agent
env.close()
if __name__ == "__main__":
parser = default_argument_parser("OpEn-trajectory-optimizer-example")
args = parser.parse_args()
main(
scenarios=args.scenarios,
sim_name=args.sim_name,
headless=args.headless,
num_episodes=args.episodes,
seed=args.seed,
)
or (psutil.cpu_count() / 2))
ray.init(num_cpus=max(num_cpus, 1))
ray.wait([
train.remote(
training_scenarios,
evaluation_scenarios,
sim_name,
headless,
num_episodes,
seed,
)
])
if __name__ == "__main__":
parser = default_argument_parser("pytorch-example")
parser.add_argument(
"--evaluation-scenario",
default="scenarios/loop",
help="The scenario to use for evaluation.",
type=str,
)
args = parser.parse_args()
main(
training_scenarios=args.scenarios,
evaluation_scenarios=[args.evaluation_scenario],
sim_name=args.sim_name,
headless=args.headless,
num_episodes=args.episodes,
seed=args.seed,
# envision_record_data_replay_path="./data_replay",
)
for episode in episodes(n=num_episodes):
agent = agent_spec.build_agent()
observations = env.reset()
episode.record_scenario(env.scenario_log)
dones = {"__all__": False}
while not dones["__all__"]:
agent_obs = observations[AGENT_ID]
agent_action = agent.act(agent_obs)
observations, rewards, dones, infos = env.step(
{AGENT_ID: agent_action})
episode.record_step(observations, rewards, dones, infos)
env.close()
if __name__ == "__main__":
parser = default_argument_parser("trajectory-tracking-agent-example")
args = parser.parse_args()
main(
scenarios=args.scenarios,
sim_name=args.sim_name,
headless=args.headless,
num_episodes=args.episodes,
seed=args.seed,
)
agent_id: agent_spec.build_agent()
for agent_id, agent_spec in agent_specs.items()
}
observations = env.reset()
episode.record_scenario(env.scenario_log)
dones = {"__all__": False}
while not dones["__all__"]:
actions = {
agent_id: agents[agent_id].act(agent_obs)
for agent_id, agent_obs in observations.items()
}
observations, rewards, dones, infos = env.step(actions)
episode.record_step(observations, rewards, dones, infos)
env.close()
if __name__ == "__main__":
parser = default_argument_parser("multi-agent-example")
args = parser.parse_args()
main(
scenarios=args.scenarios,
sim_name=args.sim_name,
headless=args.headless,
num_episodes=args.episodes,
seed=args.seed,
)
}
batched_actions.append(actions)
# Step all environments in parallel
(
batched_observations,
batched_rewards,
batched_dones,
batched_infos,
) = env.step(batched_actions)
env.close()
if __name__ == "__main__":
parser = default_argument_parser("parallel-environment-example")
parser.add_argument(
"--num-agents",
default=2,
type=int,
help="Number of ego agents to simulate in each environment.",
)
parser.add_argument(
"--num-stack",
default=2,
type=int,
help=
"Number of consecutive frames to stack in each environment's observation.",
)
parser.add_argument(
"--num-env",
visdom=False,
seed=seed,
fixed_timestep_sec=0.1,
)
if max_episode_steps is None:
max_episode_steps = 1000
for episode in episodes(n=num_episodes):
env.reset()
episode.record_scenario(env.scenario_log)
for _ in range(max_episode_steps):
env.step({})
episode.record_step({}, {}, {}, {})
env.close()
if __name__ == "__main__":
parser = default_argument_parser("egoless-example")
args = parser.parse_args()
main(
scenarios=args.scenarios,
sim_name=args.sim_name,
headless=args.headless,
num_episodes=args.episodes,
seed=args.seed,
)
# Wrap a single-agent env with SingleAgent wrapper to make `step` and `reset`
# output compliant with gym spaces.
env = SingleAgent(env)
for episode in episodes(n=num_episodes):
agent = agent_spec.build_agent()
observation = env.reset()
episode.record_scenario(env.scenario_log)
done = False
while not done:
agent_action = agent.act(observation)
observation, reward, done, info = env.step(agent_action)
episode.record_step(observation, reward, done, info)
env.close()
if __name__ == "__main__":
parser = default_argument_parser("single-agent-example")
args = parser.parse_args()
main(
scenarios=args.scenarios,
sim_name=args.sim_name,
headless=args.headless,
num_episodes=args.episodes,
seed=args.seed,
)