1566 - added test file and edited configs to include types of num steps and modifed agents to use correct step and episode counts

tests/config/legacy_conversion/new_training_config.yaml

@@ -20,10 +20,17 @@ agent_identifier: PPO
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 # Time delay between steps (for generic agents)
 time_delay: 10
 # Type of session to be run (TRAINING or EVALUATION)

tests/config/obs_tests/main_config_LINK_TRAFFIC_LEVELS.yaml

@@ -22,10 +22,17 @@ agent_identifier: A2C
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 
 
 observation_space:

tests/config/obs_tests/main_config_NODE_LINK_TABLE.yaml

@@ -22,10 +22,17 @@ agent_identifier: RANDOM
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 
 observation_space:
   components:

tests/config/obs_tests/main_config_NODE_STATUSES.yaml

@@ -22,10 +22,17 @@ agent_identifier: RANDOM
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 
 observation_space:
   components:

tests/config/obs_tests/main_config_without_obs.yaml

@@ -22,10 +22,17 @@ agent_identifier: RANDOM
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 # Time delay between steps (for generic agents)
 time_delay: 1
 # Type of session to be run (TRAINING or EVALUATION)

tests/config/one_node_states_on_off_main_config.yaml

@@ -22,10 +22,17 @@ agent_identifier: DUMMY
 # "ACL"
 # "ANY" node and acl actions
 action_type: NODE
-# Number of episodes to run per session
-num_episodes: 1
-# Number of time_steps per episode
-num_steps: 15
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 # Time delay between steps (for generic agents)
 time_delay: 1
 

tests/config/single_action_space_fixed_blue_actions_main_config.yaml

@@ -22,10 +22,17 @@ agent_identifier: RANDOM
 # "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: 15
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 # Time delay between steps (for generic agents)
 time_delay: 1
 # Type of session to be run (TRAINING or EVALUATION)

tests/config/single_action_space_main_config.yaml

@@ -22,10 +22,17 @@ agent_identifier: RANDOM
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 # Time delay between steps (for generic agents)
 time_delay: 1
 # Type of session to be run (TRAINING or EVALUATION)

tests/config/test_random_red_main_config.yaml

@@ -28,10 +28,17 @@ random_red_agent: True
 # "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
+# Number of episodes for training to run per session
+num_train_episodes: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 256
 # Time delay between steps (for generic agents)
 time_delay: 1
 

tests/config/train_episode_step.yaml

@@ -0,0 +1,153 @@
+# 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
+
+# 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: 30
+
+# Number of time_steps for training per episode
+num_train_steps: 1
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 10
+
+# 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: 10
+
+# 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: EVAL
+
+# 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: -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/config/train_eval_check_episode_step.yaml

@@ -0,0 +1,153 @@
+# 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
+
+# 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: 30
+
+# Number of time_steps for training per episode
+num_train_steps: 1
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# Number of time_steps for evaluation per episode
+num_eval_steps: 10
+
+# 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: 10
+
+# 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: -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/config/training_config_main.yaml

@@ -0,0 +1,153 @@
+# 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
+
+# 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: 10
+
+# Number of time_steps for training per episode
+num_train_steps: 256
+
+# Number of episodes for evaluation to run per session
+num_eval_episodes: 10
+
+# 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: 10
+
+# 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: -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/conftest.py

@@ -163,8 +163,9 @@ def run_generic(env, config_values):
     """Run against a generic agent."""
     # Reset the environment at the start of the episode
     # env.reset()
-    for episode in range(0, config_values.num_episodes):
-        for step in range(0, config_values.num_steps):
+    print(config_values.num_train_episodes, "how many episodes")
+    for episode in range(0, config_values.num_train_episodes):
+        for step in range(0, config_values.num_train_steps):
             # Send the observation space to the agent to get an action
             # TEMP - random action for now
             # action = env.blue_agent_action(obs)

tests/test_single_action_space.py

@@ -12,8 +12,8 @@ def run_generic_set_actions(env: Primaite):
     # Reset the environment at the start of the episode
     # env.reset()
     training_config = env.training_config
-    for episode in range(0, training_config.num_episodes):
-        for step in range(0, training_config.num_steps):
+    for episode in range(0, training_config.num_train_episodes):
+        for step in range(0, training_config.num_train_steps):
             # Send the observation space to the agent to get an action
             # TEMP - random action for now
             # action = env.blue_agent_action(obs)

tests/test_train_eval_episode_steps.py

@@ -0,0 +1,46 @@
+import pytest
+
+from primaite import getLogger
+from primaite.config.lay_down_config import dos_very_basic_config_path
+from tests import TEST_CONFIG_ROOT
+from tests.conftest import run_generic
+
+_LOGGER = getLogger(__name__)
+
+
+@pytest.mark.parametrize(
+    "temp_primaite_session",
+    [[TEST_CONFIG_ROOT / "train_episode_step.yaml", dos_very_basic_config_path()]],
+    indirect=True,
+)
+def test_eval_steps_differ_from_training(temp_primaite_session):
+    """Uses PrimaiteSession class to compare number of episodes used for training and evaluation."""
+    with temp_primaite_session as train_session:
+        env = train_session.env
+        train_session.learn()
+
+    """
+    Train_episode_step.yaml main config:
+    num_train_steps = 1
+    num_eval_steps = 10
+
+    When the YAML file changes from TRAIN to EVAL the episode step changes and uses the other config value.
+
+    The test is showing that 10 steps are running for evaluation and NOT 1 step as EVAL has been selected in the config.
+    """
+    assert env.episode_steps == 10  # 30
+    # assert env.actual_episode_count == 10 # should be 10
+
+
+@pytest.mark.parametrize(
+    "temp_primaite_session",
+    [[TEST_CONFIG_ROOT / "train_episode_step.yaml", dos_very_basic_config_path()]],
+    indirect=True,
+)
+def test_train_eval_config_option(temp_primaite_session):
+    """Uses PrimaiteSession class to test number of episodes and steps used for TRAIN and EVAL option."""
+    with temp_primaite_session as train_session:
+        env = train_session.env
+        run_generic(env, env.training_config)
+
+    print(env.actual_episode_count, env.step_count, env.total_step_count)