Rescaled default rewards by a factor of 1/10000

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

@@ -83,58 +83,58 @@ sb3_output_verbose_level: NONE
 # 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
+off_should_be_on: -0.001
+off_should_be_resetting: -0.0005
+on_should_be_off: -0.0002
+on_should_be_resetting: -0.0005
+resetting_should_be_on: -0.0005
+resetting_should_be_off: -0.0002
+resetting: -0.0003
 # 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
+good_should_be_patching: 0.0002
+good_should_be_compromised: 0.0005
+good_should_be_overwhelmed: 0.0005
+patching_should_be_good: -0.0005
+patching_should_be_compromised: 0.0002
+patching_should_be_overwhelmed: 0.0002
+patching: -0.0003
+compromised_should_be_good: -0.002
+compromised_should_be_patching: -0.002
+compromised_should_be_overwhelmed: -0.002
+compromised: -0.002
+overwhelmed_should_be_good: -0.002
+overwhelmed_should_be_patching: -0.002
+overwhelmed_should_be_compromised: -0.002
+overwhelmed: -0.002
 # 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
+good_should_be_repairing: 0.0002
+good_should_be_restoring: 0.0002
+good_should_be_corrupt: 0.0005
+good_should_be_destroyed: 0.001
+repairing_should_be_good: -0.0005
+repairing_should_be_restoring: 0.0002
+repairing_should_be_corrupt: 0.0002
+repairing_should_be_destroyed: 0.0000
+repairing: -0.0003
+restoring_should_be_good: -0.001
+restoring_should_be_repairing: -0.0002
+restoring_should_be_corrupt: 0.0001
+restoring_should_be_destroyed: 0.0002
+restoring: -0.0006
+corrupt_should_be_good: -0.001
+corrupt_should_be_repairing: -0.001
+corrupt_should_be_restoring: -0.001
+corrupt_should_be_destroyed: 0.0002
+corrupt: -0.001
+destroyed_should_be_good: -0.002
+destroyed_should_be_repairing: -0.002
+destroyed_should_be_restoring: -0.002
+destroyed_should_be_corrupt: -0.002
+destroyed: -0.002
+scanning: -0.0002
 # IER status
-red_ier_running: -5
-green_ier_blocked: -10
+red_ier_running: -0.0005
+green_ier_blocked: -0.001
 
 # Patching / Reset durations
 os_patching_duration: 5            # The time taken to patch the OS

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

@@ -37,60 +37,60 @@ observation_space_high_value: 1000000000
 
 # Reward values
 # Generic
-all_ok: 0
+all_ok: 0.0000
 # 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
+off_should_be_on: -0.001
+off_should_be_resetting: -0.0005
+on_should_be_off: -0.0002
+on_should_be_resetting: -0.0005
+resetting_should_be_on: -0.0005
+resetting_should_be_off: -0.0002
+resetting: -0.0003
 # 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
+good_should_be_patching: 0.0002
+good_should_be_compromised: 0.0005
+good_should_be_overwhelmed: 0.0005
+patching_should_be_good: -0.0005
+patching_should_be_compromised: 0.0002
+patching_should_be_overwhelmed: 0.0002
+patching: -0.0003
+compromised_should_be_good: -0.002
+compromised_should_be_patching: -0.002
+compromised_should_be_overwhelmed: -0.002
+compromised: -0.002
+overwhelmed_should_be_good: -0.002
+overwhelmed_should_be_patching: -0.002
+overwhelmed_should_be_compromised: -0.002
+overwhelmed: -0.002
 # 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
+good_should_be_repairing: 0.0002
+good_should_be_restoring: 0.0002
+good_should_be_corrupt: 0.0005
+good_should_be_destroyed: 0.001
+repairing_should_be_good: -0.0005
+repairing_should_be_restoring: 0.0002
+repairing_should_be_corrupt: 0.0002
+repairing_should_be_destroyed: 0.0000
+repairing: -0.0003
+restoring_should_be_good: -0.001
+restoring_should_be_repairing: -0.0002
+restoring_should_be_corrupt: 0.0001
+restoring_should_be_destroyed: 0.0002
+restoring: -0.0006
+corrupt_should_be_good: -0.001
+corrupt_should_be_repairing: -0.001
+corrupt_should_be_restoring: -0.001
+corrupt_should_be_destroyed: 0.0002
+corrupt: -0.001
+destroyed_should_be_good: -0.002
+destroyed_should_be_repairing: -0.002
+destroyed_should_be_restoring: -0.002
+destroyed_should_be_corrupt: -0.002
+destroyed: -0.002
+scanning: -0.0002
 # IER status
-red_ier_running: -5
-green_ier_blocked: -10
+red_ier_running: -0.0005
+green_ier_blocked: -0.001
 
 # Patching / Reset durations
 os_patching_duration: 5            # The time taken to patch the OS