added scenario self stop, agent setup, action masking in PPO

ai_economist/foundation/base/base_agent.py

@@ -5,6 +5,7 @@
 # or https://opensource.org/licenses/BSD-3-Clause
 
 import random
+import uuid
 
 import numpy as np
 
@@ -38,7 +39,7 @@ class BaseAgent:
 
         if idx is None:
             idx = 0
-        
+        self.uuid=uuid.uuid4()
         if multi_action_mode is None:
             multi_action_mode = False