#1522: refactor red_agent_identifier -> random_red_agent so that it is a boolean + documentation

docs/source/config.rst

@@ -28,6 +28,10 @@ The environment config file consists of the following attributes:
    * STABLE_BASELINES3_PPO - Use a SB3 PPO agent
    * STABLE_BASELINES3_A2C - use a SB3 A2C agent
 
+* **random_red_agent** [bool]
+
+    Determines if the session should be run with a random red agent
+
 * **action_type** [enum]
 
    Determines whether a NODE, ACL, or ANY (combined NODE & ACL) action space format is adopted for the session

src/primaite/config/_package_data/training/training_config_main.yaml

@@ -9,7 +9,7 @@ agent_identifier: STABLE_BASELINES3_A2C
 
 # RED AGENT IDENTIFIER
 # RANDOM or NONE
-red_agent_identifier: "NONE"
+random_red_agent: False
 
 # Sets How the Action Space is defined:
 # "NODE"

src/primaite/config/_package_data/training/training_config_random_red_agent.yaml

@@ -9,7 +9,7 @@ agent_identifier: STABLE_BASELINES3_A2C
 
 # RED AGENT IDENTIFIER
 # RANDOM or NONE
-red_agent_identifier: "RANDOM"
+random_red_agent: True
 
 # Sets How the Action Space is defined:
 # "NODE"

src/primaite/config/training_config.py

@@ -21,7 +21,7 @@ class TrainingConfig:
     agent_identifier: str = "STABLE_BASELINES3_A2C"
     "The Red Agent algo/class to be used."
 
-    red_agent_identifier: str = "RANDOM"
+    random_red_agent: bool = False
     "Creates Random Red Agent Attacks"
 
     action_type: ActionType = ActionType.ANY

src/primaite/environment/primaite_env.py

@@ -277,7 +277,7 @@ class Primaite(Env):
         self.reset_environment()
 
         # Create a random red agent to use for this episode
-        if self.training_config.red_agent_identifier == "RANDOM":
+        if self.training_config.random_red_agent:
             self.create_random_red_agent()
 
         # Reset counters and totals

tests/config/random_agent_main_config.yaml

@@ -1,96 +0,0 @@
-# Main Config File
-
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-# "GENERIC"
-agent_identifier: GENERIC
-#
-red_agent_identifier: RANDOM
-# 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: 1
-# Number of time_steps per episode
-num_steps: 5
-# Time delay between steps (for generic agents)
-time_delay: 1
-# 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: 1_000_000_000
-
-# 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

tests/test_red_random_agent_behaviour.py

@@ -55,6 +55,8 @@ def test_random_red_agent_behaviour():
             session_path=session_path,
             timestamp_str=timestamp_str,
         )
+        # set red_agent_
+        env.training_config.random_red_agent = True
         training_config = env.training_config
         training_config.num_steps = env.episode_steps