1566 - added correct num_train_episodes etc values to configs, fixed test_reward.py

tests/config/ppo_not_seeded_training_config.yaml

@@ -60,10 +60,16 @@ observation_space:
     # - name: NODE_STATUSES
     # - name: LINK_TRAFFIC_LEVELS
 # Number of episodes to run per session
-num_episodes: 10
+num_train_episodes: 10
 
 # Number of time_steps per episode
-num_steps: 256
+num_train_steps: 256
+
+# Number of episodes to run per session
+num_eval_episodes: 10
+
+# Number of time_steps 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

tests/config/ppo_seeded_training_config.yaml

@@ -60,10 +60,16 @@ observation_space:
     # - name: NODE_STATUSES
     # - name: LINK_TRAFFIC_LEVELS
 # Number of episodes to run per session
-num_episodes: 10
+num_train_episodes: 10
 
 # Number of time_steps per episode
-num_steps: 256
+num_train_steps: 256
+
+# Number of episodes to run per session
+num_eval_episodes: 1
+
+# Number of time_steps 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

tests/config/single_action_space_fixed_blue_actions_main_config.yaml

@@ -23,16 +23,11 @@ agent_identifier: RANDOM
 # "ANY" node and acl actions
 action_type: ANY
 # Number of episodes for training to run per session
-num_train_episodes: 10
+num_train_episodes: 1
 
 # Number of time_steps for training per episode
-num_train_steps: 256
+num_train_steps: 15
 
-# 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_lay_down_config.yaml

@@ -32,14 +32,6 @@
   - name: ftp
     port: '21'
     state: COMPROMISED
-- item_type: POSITION
-  positions:
-  - node: '1'
-    x_pos: 309
-    y_pos: 78
-  - node: '2'
-    x_pos: 200
-    y_pos: 78
 - item_type: RED_IER
   id: '3'
   start_step: 2

tests/config/test_random_red_main_config.yaml

@@ -29,16 +29,16 @@ random_red_agent: True
 # "ANY" node and acl actions
 action_type: NODE
 # Number of episodes for training to run per session
-num_train_episodes: 10
+num_train_episodes: 2
 
 # Number of time_steps for training per episode
-num_train_steps: 256
+num_train_steps: 15
 
 # Number of episodes for evaluation to run per session
-num_eval_episodes: 10
+num_eval_episodes: 2
 
 # Number of time_steps for evaluation per episode
-num_eval_steps: 256
+num_eval_steps: 15
 # Time delay between steps (for generic agents)
 time_delay: 1