qos_steer Adapter¶
¶
- class network_gym_client.envs.qos_steer.Adapter(config_json)[source]¶
qos_steer environment adapter.
- Parameters:
Adapter (network_gym_client.adapter.Adapter) – base class.
Initialize the adapter.
- Parameters:
config_json (json) – the configuration file
Methods¶
- network_gym_client.envs.qos_steer.Adapter.get_observation(self, df)¶
Prepare observation for qos_steer env.
This function should return the same number of features defined in the
get_observation_space().- Parameters:
df (pd.DataFrame) – network stats measurement
- Returns:
spaces – observation spaces
- network_gym_client.envs.qos_steer.Adapter.get_reward(self, df)¶
Prepare reward for qos_steer env.
- Parameters:
df (pd.DataFrame]) – network stats measurement
- Returns:
spaces – reward space
- network_gym_client.envs.qos_steer.Adapter.get_policy(self, action)¶
Prepare network policy for qos_steer env.
- Parameters:
action (spaces) – action from RL agent
- Returns:
json – network policy
Reward Methods¶
- network_gym_client.envs.qos_steer.Adapter.calculate_wifi_qos_user_num(self, qos_rate)¶
Calculate the number of QoS users over Wi-Fi. Default reward function.
- Parameters:
qos_rate (pandas.DataFrame) – qos data rate per user
- Returns:
double – reward
Additional Methods¶
- network_gym_client.envs.qos_steer.Adapter.get_action_space(self)¶
Get action space for qos_steer env.
- Returns:
spaces – action spaces
- network_gym_client.envs.qos_steer.Adapter.get_observation_space(self)¶
Get observation space for qos_steer env.
- Returns:
spaces – observation spaces