901 - changed acl current obs from list to numpy.array, changed default ACL list in training_config.py to FALSE, and tried to make test_seeding_and_deterministic_session.py test without fixed reward results

tests/config/obs_tests/main_config_ACCESS_CONTROL_LIST.yaml

@@ -5,7 +5,8 @@
 # "STABLE_BASELINES3_PPO"
 # "STABLE_BASELINES3_A2C"
 # "GENERIC"
-agent_identifier: STABLE_BASELINES3_A2C
+agent_framework: SB3
+agent_identifier: PPO
 # Sets How the Action Space is defined:
 # "NODE"
 # "ACL"
@@ -21,7 +22,7 @@ apply_implicit_rule: True
 # Implicit ACL firewall rule at end of lists to be default action or no rule can be selected (ALLOW or DENY)
 implicit_acl_rule: DENY
 # Total number of ACL rules allowed in the environment
-max_number_acl_rules: 10
+max_number_acl_rules: 3
 
 observation_space:
   components:
@@ -31,7 +32,7 @@ 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/single_action_space_main_config.yaml

@@ -39,6 +39,8 @@ agent_load_file: C:\[Path]\[agent_saved_filename.zip]
 # The high value for the observation space
 observation_space_high_value: 1000000000
 
+# Choice whether to have an ALLOW or DENY implicit rule or not (TRUE or FALSE)
+apply_implicit_rule: True
 implicit_acl_rule: DENY
 max_number_acl_rules: 10
 # Reward values