RE-ran the benchmarks for v2.0.0rc1 and v2.0.0rc2 using the same config file. As expected, the versions perform almost identically as there's no real logic changes that would affect the agent between the two release candidates

benchmark/config/benchmark_training_config.yaml

@@ -0,0 +1,164 @@
+# © Crown-owned copyright 2023, Defence Science and Technology Laboratory UK
+# 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 deep learning framework will be used (by RLlib ONLY).
+# Default is TF (Tensorflow).
+# Options are:
+# "TF" (Tensorflow)
+# TF2 (Tensorflow 2.X)
+# TORCH (PyTorch)
+deep_learning_framework: TF2
+
+# 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: PPO
+
+# Sets whether Red Agent POL and IER is randomised.
+# Options are:
+# True
+# False
+random_red_agent: False
+
+# The (integer) seed to be used in random number generation
+# Default is None (null)
+seed: null
+
+# Set whether the agent will be deterministic instead of stochastic
+# Options are:
+# True
+# False
+deterministic: False
+
+# Sets what view of the environment the deterministic hardcoded agent has. The default is BASIC.
+# Options are:
+# "BASIC" (The current observation space only)
+# "FULL" (Full environment view with actions taken and reward feedback)
+hard_coded_agent_view: FULL
+
+# Sets How the Action Space is defined:
+# "NODE"
+# "ACL"
+# "ANY" node and acl actions
+action_type: NODE
+
+# observation space
+observation_space:
+  flatten: true
+  components:
+    - name: NODE_LINK_TABLE
+    - name: NODE_STATUSES
+    - name: LINK_TRAFFIC_LEVELS
+
+# Number of episodes for training to run per session
+num_train_episodes: 500
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 1
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
+
+# Sets how often the agent will save a checkpoint (every n time episodes).
+# Set to 0 if no checkpoints are required. Default is 10
+checkpoint_every_n_episodes: 0
+
+# Time delay (milliseconds) between steps for CUSTOM agents.
+time_delay: 5
+
+# Type of session to be run. Options are:
+# "TRAIN" (Trains an agent)
+# "EVAL" (Evaluates an agent)
+# "TRAIN_EVAL" (Trains then evaluates an agent)
+session_type: TRAIN
+
+# Environment config values
+# The high value for the observation space
+observation_space_high_value: 1000000000
+
+# The Stable Baselines3 learn/eval output verbosity level:
+# Options are:
+# "NONE" (No Output)
+# "INFO" (Info Messages (such as devices and wrappers used))
+# "DEBUG" (All Messages)
+sb3_output_verbose_level: NONE
+
+# Reward values
+# Generic
+all_ok: 0
+# Node Hardware State
+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: 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: 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: -0.0005
+green_ier_blocked: -0.001
+
+# 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