made a bit of progress

main.py

@@ -45,7 +45,7 @@ env_config = {
         # (3) Movement and resource collection
         ('SimpleGather', {}),
         ('ExternalMarket',{'market_demand':{
-            'Gem': 15
+            'Gem': 11
         }}),
     ],
     
@@ -57,7 +57,7 @@ env_config = {
     
     # ===== STANDARD ARGUMENTS ======
     # kwargs that are used by every Scenario class (i.e. defined in BaseEnvironment)
-    'agent_composition': {"BasicMobileAgent": 20,"TradingAgent":5},        # Number of non-planner agents (must be > 1)
+    'agent_composition': {"BasicMobileAgent": 10,"TradingAgent":10},        # Number of non-planner agents (must be > 1)
     'world_size': [5, 5], # [Height, Width] of the env world
     'episode_length': 256, # Number of timesteps per episode
     'isoelastic_eta':0.001,
@@ -242,7 +242,7 @@ econ=foundation.make_env_instance(**env_config)
 
 market=econ.get_component("ContinuousDoubleAuction")
 action=market.get_n_actions("TradingAgent")
-baseEconWrapper=BaseEconWrapper(econ)
+baseEconWrapper=BaseEconWrapper(econ,True)
 baseEconWrapper.run()
 time.sleep(0.5)
 mobileRecieverEconWrapper=RecieverEconWrapper(base_econ=baseEconWrapper,agent_classname="BasicMobileAgent")
@@ -262,7 +262,7 @@ stackenv_traid=vec_frame_stack.VecFrameStack(venv=montraidingenv,n_stack=num_fra
 econ_eval=foundation.make_env_instance(**eval_env_config)
 
 
-baseEconWrapper_eval=BaseEconWrapper(econ_eval)
+baseEconWrapper_eval=BaseEconWrapper(econ_eval,False)
 baseEconWrapper_eval.run()
 time.sleep(0.5)
 mobileRecieverEconWrapper_eval=RecieverEconWrapper(base_econ=baseEconWrapper_eval,agent_classname="BasicMobileAgent")
@@ -325,6 +325,7 @@ while True:
    
     ## Run Eval
     print("### EVAL ###")
+    baseEconWrapper_eval.force_reset()
     obs_basic=stackenv_basic_eval.reset()
     obs_trade=stackenv_traid_eval.reset()
     done=False