273876873e
- renamed _config_values_main to training_config.py and renamed the ConfigValuesMain class to TrainingConfig. Moved training_config.py to src/primaite/config/training_config.py - Renamed all training config yaml file keys to make creating an instance of TrainingConfig easier. Moved action_type and num_steps over to the training config. - Decoupled the training config and lay down config. - Refactored main.py so that it can be ran from CLI and can take a training config path and a lay down config path. - refactored all outputs so that they save to the session dir. - Added some necessary setup scripts that handle creating app dirs, fronting example config files to the user, fronting demo notebooks to the user, performing clean-up in between installations etc. - Added functions that attempt to retrieve the file path of users example config files that have been fronted by the primaite setup. - Added logging config and a getLogger function in the top-level init. - Refactored all logs entries logged to use a logger using the primaite logging config. - Added basic typer CLI for doing things like setup, viewing logs, viewing primaite version, running a basic session. - Updated test to use new features and config structures. - Began updating docs. More to do here.
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
from tests import TEST_CONFIG_ROOT
|
|
from tests.conftest import _get_primaite_env_from_config
|
|
|
|
|
|
def test_rewards_are_being_penalised_at_each_step_function():
|
|
"""
|
|
Test that hardware state is penalised at each step.
|
|
|
|
When the initial state is OFF compared to reference state which is ON.
|
|
"""
|
|
env = _get_primaite_env_from_config(
|
|
training_config_path=TEST_CONFIG_ROOT
|
|
/ "one_node_states_on_off_main_config.yaml",
|
|
lay_down_config_path=TEST_CONFIG_ROOT
|
|
/ "one_node_states_on_off_lay_down_config.yaml",
|
|
)
|
|
|
|
"""
|
|
On different steps (of the 13 in total) these are the following rewards for config_6 which are activated:
|
|
File System State: goodShouldBeCorrupt = 5 (between Steps 1 & 3)
|
|
Hardware State: onShouldBeOff = -2 (between Steps 4 & 6)
|
|
Service State: goodShouldBeCompromised = 5 (between Steps 7 & 9)
|
|
Software State (Software State): goodShouldBeCompromised = 5 (between Steps 10 & 12)
|
|
|
|
Total Reward: -2 - 2 + 5 + 5 + 5 + 5 + 5 + 5 = 26
|
|
Step Count: 13
|
|
|
|
For the 4 steps where this occurs the average reward is:
|
|
Average Reward: 2 (26 / 13)
|
|
"""
|
|
print("average reward", env.average_reward)
|
|
assert env.average_reward == -8.0
|