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.
95 lines
2.7 KiB
YAML
95 lines
2.7 KiB
YAML
# Main Config File
|
|
|
|
# Generic config values
|
|
# Choose one of these (dependent on Agent being trained)
|
|
# "STABLE_BASELINES3_PPO"
|
|
# "STABLE_BASELINES3_A2C"
|
|
# "GENERIC"
|
|
agent_identifier: STABLE_BASELINES3_A2C
|
|
# Sets How the Action Space is defined:
|
|
# "NODE"
|
|
# "ACL"
|
|
# "ANY" node and acl actions
|
|
action_type: ANY
|
|
# Number of episodes to run per session
|
|
num_episodes: 10
|
|
# Number of time_steps per episode
|
|
num_steps: 256
|
|
# Time delay between steps (for generic agents)
|
|
time_delay: 10
|
|
# Type of session to be run (TRAINING or EVALUATION)
|
|
session_type: TRAINING
|
|
# Determine whether to load an agent from file
|
|
load_agent: False
|
|
# File path and file name of agent if you're loading one in
|
|
agent_load_file: C:\[Path]\[agent_saved_filename.zip]
|
|
|
|
# Environment config values
|
|
# The high value for the observation space
|
|
observation_space_high_value: 1000000000
|
|
|
|
# Reward values
|
|
# Generic
|
|
all_ok: 0
|
|
# Node Hardware State
|
|
off_should_be_on: -10
|
|
off_should_be_resetting: -5
|
|
on_should_be_off: -2
|
|
on_should_be_resetting: -5
|
|
resetting_should_be_on: -5
|
|
resetting_should_be_off: -2
|
|
resetting: -3
|
|
# Node Software or Service State
|
|
good_should_be_patching: 2
|
|
good_should_be_compromised: 5
|
|
good_should_be_overwhelmed: 5
|
|
patching_should_be_good: -5
|
|
patching_should_be_compromised: 2
|
|
patching_should_be_overwhelmed: 2
|
|
patching: -3
|
|
compromised_should_be_good: -20
|
|
compromised_should_be_patching: -20
|
|
compromised_should_be_overwhelmed: -20
|
|
compromised: -20
|
|
overwhelmed_should_be_good: -20
|
|
overwhelmed_should_be_patching: -20
|
|
overwhelmed_should_be_compromised: -20
|
|
overwhelmed: -20
|
|
# Node File System State
|
|
good_should_be_repairing: 2
|
|
good_should_be_restoring: 2
|
|
good_should_be_corrupt: 5
|
|
good_should_be_destroyed: 10
|
|
repairing_should_be_good: -5
|
|
repairing_should_be_restoring: 2
|
|
repairing_should_be_corrupt: 2
|
|
repairing_should_be_destroyed: 0
|
|
repairing: -3
|
|
restoring_should_be_good: -10
|
|
restoring_should_be_repairing: -2
|
|
restoring_should_be_corrupt: 1
|
|
restoring_should_be_destroyed: 2
|
|
restoring: -6
|
|
corrupt_should_be_good: -10
|
|
corrupt_should_be_repairing: -10
|
|
corrupt_should_be_restoring: -10
|
|
corrupt_should_be_destroyed: 2
|
|
corrupt: -10
|
|
destroyed_should_be_good: -20
|
|
destroyed_should_be_repairing: -20
|
|
destroyed_should_be_restoring: -20
|
|
destroyed_should_be_corrupt: -20
|
|
destroyed: -20
|
|
scanning: -2
|
|
# IER status
|
|
red_ier_running: -5
|
|
green_ier_blocked: -10
|
|
|
|
# Patching / Reset durations
|
|
os_patching_duration: 5 # The time taken to patch the OS
|
|
node_reset_duration: 5 # The time taken to reset a node (hardware)
|
|
service_patching_duration: 5 # The time taken to patch a service
|
|
file_system_repairing_limit: 5 # The time take to repair the file system
|
|
file_system_restoring_limit: 5 # The time take to restore the file system
|
|
file_system_scanning_limit: 5 # The time taken to scan the file system
|