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

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