diff --git a/Macodiac.ML/multiagent_main.py b/Macodiac.ML/multiagent_main.py
index a3329d4..bf4bb18 100644
--- a/Macodiac.ML/multiagent_main.py
+++ b/Macodiac.ML/multiagent_main.py
@@ -25,7 +25,7 @@ def __init__(self):
         self.save_path =  os.path.join(filePath,'saved_models', 'model')
         self.save_path_intermittent =  os.path.join(filePath,'saved_models', 'intermittent_saved_models')
         self.numTrainingIterations = 1_000
-        self.numEpisodes = 15
+        self.numEpisodes = 150
         self.envTimesteps = 15
         self.numAgents = 10
 
@@ -87,7 +87,7 @@ def run_multiagent_project_with_rand_test(self, env:MultiAgentMacodiacEnvironmen
                 iterator+=1
                 print(f'iterator:{iterator}')
                 action_arr = env.action_space.sample()
-                
+
                 print(f'action for agents:\t{action_arr}')
                 
                 obs_arr, reward, isDone, info_arr = env.step(action_arr)
diff --git a/Macodiac.ML/multiagentenvironment.py b/Macodiac.ML/multiagentenvironment.py
index c8e80ad..bcd543b 100644
--- a/Macodiac.ML/multiagentenvironment.py
+++ b/Macodiac.ML/multiagentenvironment.py
@@ -54,7 +54,7 @@ def __init__(self, envTimesteps:int, numAgents: int):
 
         self.action_space = spaces.MultiDiscrete(arr)
 
-        # the observation space is a nAgents by nActions array of float32 numbers between 0-100
+        # the observation space is a nAgents by nActions array of float32 numbers between -99-99
         # also contains the static value for marginal cost and wholesale price
         self.observation_space = spaces.Box(low=-100,high=100, shape=(numAgents, 4), dtype=np.float32)
 
@@ -80,7 +80,7 @@ def set_agent_action(self, action, agent, actionSpace):
         agentBaseVendingPriceAdjust = self.env_wholesale_price * (agent.state / 100)
         baseAgentVendingPrice = self.env_wholesale_price + agentBaseVendingPriceAdjust
         #agentMarginalCostAddedVendingPrice = agentBaseVendingPriceAdjust + self.env_agent_marginal_cost
-        agent.vendingPrice = baseAgentVendingPrice
+        agent.vendingPrice = max(baseAgentVendingPrice, 1)
         # print(f'agent vending price was {agent.vendingPrice}')
 
     def step_agent(self, agent):
@@ -268,4 +268,4 @@ def get_consumer_quantity_demanded_at_price(self, price):
 
 
     def get_agent_default_observation_array(self):
-        return [0.0, 0.0, 60.0, 5.0]
\ No newline at end of file
+        return [0.0, 0.0, self.env_wholesale_price, self.env_agent_marginal_cost]
\ No newline at end of file