Merge branch 'dev' into feature/1386-enable-a-repeatable-or-deterministic-baseline-test

tests/config/legacy_conversion/new_training_config.yaml

@@ -1,11 +1,20 @@
 # 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 which agent algorithm framework will be used:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray[RLlib])
+# "NONE" (Custom Agent)
+agent_framework: SB3
+
+# Sets which Red Agent algo/class will be used:
+# "PPO" (Proximal Policy Optimization)
+# "A2C" (Advantage Actor Critic)
+# "HARDCODED" (Custom Agent)
+# "RANDOM" (Random Action)
+agent_identifier: PPO
+
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -18,7 +27,7 @@ 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
+session_type: TRAIN
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/obs_tests/main_config_LINK_TRAFFIC_LEVELS.yaml

@@ -1,11 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: SB3
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: A2C
 
-# 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"
@@ -28,7 +39,7 @@ observation_space:
 time_delay: 1
 
 # Type of session to be run (TRAINING or EVALUATION)
-session_type: TRAINING
+session_type: TRAIN
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/obs_tests/main_config_NODE_LINK_TABLE.yaml

@@ -1,11 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: RANDOM
 
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-# "GENERIC"
-agent_identifier: NONE
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -24,7 +35,7 @@ observation_space:
 time_delay: 1
 # Filename of the scenario / laydown
 
-session_type: TRAINING
+session_type: TRAIN
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/obs_tests/main_config_NODE_STATUSES.yaml

@@ -1,11 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: RANDOM
 
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-# "GENERIC"
-agent_identifier: NONE
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -25,7 +36,7 @@ observation_space:
 time_delay: 1
 
 # Type of session to be run (TRAINING or EVALUATION)
-session_type: TRAINING
+session_type: TRAIN
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/obs_tests/main_config_without_obs.yaml

@@ -1,11 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: RANDOM
 
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-# "GENERIC"
-agent_identifier: NONE
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -18,7 +29,7 @@ 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
+session_type: TRAIN
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/one_node_states_on_off_main_config.yaml

@@ -1,10 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: DUMMY
 
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-agent_identifier: GENERIC
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -18,7 +30,7 @@ num_steps: 15
 time_delay: 1
 
 # Type of session to be run (TRAINING or EVALUATION)
-session_type: TRAINING
+session_type: EVAL
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/single_action_space_fixed_blue_actions_main_config.yaml

@@ -1,11 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: RANDOM
 
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-# "GENERIC"
-agent_identifier: GENERIC
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -18,7 +29,7 @@ num_steps: 15
 # Time delay between steps (for generic agents)
 time_delay: 1
 # Type of session to be run (TRAINING or EVALUATION)
-session_type: TRAINING
+session_type: EVAL
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/single_action_space_main_config.yaml

@@ -1,11 +1,22 @@
-# Main Config File
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: RANDOM
 
-# Generic config values
-# Choose one of these (dependent on Agent being trained)
-# "STABLE_BASELINES3_PPO"
-# "STABLE_BASELINES3_A2C"
-# "GENERIC"
-agent_identifier: GENERIC
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -18,7 +29,7 @@ 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
+session_type: EVAL
 # Determine whether to load an agent from file
 load_agent: False
 # File path and file name of agent if you're loading one in

tests/config/test_random_red_main_config.yaml

@@ -0,0 +1,112 @@
+# Training Config File
+
+# Sets which agent algorithm framework will be used.
+# Options are:
+# "SB3" (Stable Baselines3)
+# "RLLIB" (Ray RLlib)
+# "CUSTOM" (Custom Agent)
+agent_framework: CUSTOM
+
+# Sets which Agent class will be used.
+# Options are:
+# "A2C" (Advantage Actor Critic coupled with either SB3 or RLLIB agent_framework)
+# "PPO" (Proximal Policy Optimization coupled with either SB3 or RLLIB agent_framework)
+# "HARDCODED" (The HardCoded agents coupled with an ACL or NODE action_type)
+# "DO_NOTHING" (The DoNothing agents coupled with an ACL or NODE action_type)
+# "RANDOM" (primaite.agents.simple.RandomAgent)
+# "DUMMY" (primaite.agents.simple.DummyAgent)
+agent_identifier: DUMMY
+
+# Sets whether Red Agent POL and IER is randomised.
+# Options are:
+# True
+# False
+random_red_agent: True
+
+# Sets How the Action Space is defined:
+# "NODE"
+# "ACL"
+# "ANY" node and acl actions
+action_type: NODE
+# Number of episodes to run per session
+num_episodes: 2
+# Number of time_steps per episode
+num_steps: 15
+# Time delay between steps (for generic agents)
+time_delay: 1
+
+# Type of session to be run (TRAINING or EVALUATION)
+session_type: EVAL
+# 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