def test_api():
env = SumoEnvironment(single_agent=True,
num_seconds=100000,
net_file='nets/single-intersection/single-intersection.net.xml',
route_file='nets/single-intersection/single-intersection.rou.xml')
env.reset()
check_env(env)
env.close()
ql_agents = {
ts: QLAgent(starting_state=env.encode(initial_states[ts], ts),
state_space=env.observation_space,
action_space=env.action_space,
alpha=args.alpha,
gamma=args.gamma,
exploration_strategy=EpsilonGreedy(
initial_epsilon=args.epsilon,
min_epsilon=args.min_epsilon,
decay=args.decay))
for ts in env.ts_ids
}
done = {'__all__': False}
infos = []
if args.fixed:
while not done['__all__']:
_, _, done, _ = env.step({})
else:
while not done['__all__']:
actions = {ts: ql_agents[ts].act() for ts in ql_agents.keys()}
s, r, done, _ = env.step(action=actions)
for agent_id in ql_agents.keys():
ql_agents[agent_id].learn(next_state=env.encode(
s[agent_id], agent_id),
reward=r[agent_id])
env.save_csv(out_csv, run)
env.close()
