add pair to environment for access inside calculate_reward

docs/freqai-reinforcement-learning.md

@@ -175,10 +175,20 @@ As you begin to modify the strategy and the prediction model, you will quickly r
                 pnl = self.get_unrealized_profit()
 
                 factor = 100
-                # reward agent for entering trades
-                if action in (Actions.Long_enter.value, Actions.Short_enter.value) \
-                        and self._position == Positions.Neutral:
-                    return 25
+
+            # you can use feature values from dataframe
+            rsi_now = self.df[f"%-rsi-period-10_shift-1_{self.pair}_"
+                              f"{self.config['timeframe']}"].iloc[self._current_tick]
+
+            # reward agent for entering trades
+            if (action in (Actions.Long_enter.value, Actions.Short_enter.value)
+                    and self._position == Positions.Neutral):
+                if rsi_now < 40:
+                    factor = 40 / rsi_now
+                else:
+                    factor = 1
+                return 25 * factor
+
                 # discourage agent from not entering trades
                 if action == Actions.Neutral.value and self._position == Positions.Neutral:
                     return -1