fix position_value to scalar

rl_agent/env.py

@@ -1,5 +1,6 @@
 import numpy as np
 import pandas as pd
+import torch
 
 class Environment:
     
@@ -37,6 +38,8 @@ class Environment:
         self.history.pop(0)
         self.history.append(self.data.iloc[self.t, :]['Close'] - self.data.iloc[(self.t-1), :]['Close']) # the price being traded
         
+        self.position_value = self.position_value.item()
+
         return [self.position_value] + self.history, reward, self.done # obs, reward, done