diff --git a/freqtrade/freqai/RL/Base4ActionRLEnv.py b/freqtrade/freqai/RL/Base4ActionRLEnv.py
index b4fe78b71..0c719ea92 100644
--- a/freqtrade/freqai/RL/Base4ActionRLEnv.py
+++ b/freqtrade/freqai/RL/Base4ActionRLEnv.py
@@ -74,6 +74,7 @@ class Base4ActionRLEnv(BaseEnvironment):
                 self._last_trade_tick = self._current_tick
             elif action == Actions.Exit.value:
                 self._position = Positions.Neutral
+                self._update_total_profit()
                 trade_type = "neutral"
                 self._last_trade_tick = None
             else:
diff --git a/freqtrade/freqai/RL/Base5ActionRLEnv.py b/freqtrade/freqai/RL/Base5ActionRLEnv.py
index 663ecc77e..b6ebcf703 100644
--- a/freqtrade/freqai/RL/Base5ActionRLEnv.py
+++ b/freqtrade/freqai/RL/Base5ActionRLEnv.py
@@ -75,8 +75,6 @@ class Base5ActionRLEnv(BaseEnvironment):
         if self._current_tick == self._end_tick:
             self._done = True
 
-        self.update_portfolio_log_returns(action)
-
         self._update_unrealized_total_profit()
         step_reward = self.calculate_reward(action)
         self.total_reward += step_reward
diff --git a/freqtrade/freqai/RL/BaseEnvironment.py b/freqtrade/freqai/RL/BaseEnvironment.py
index 6633bf3e8..3b56fc2c4 100644
--- a/freqtrade/freqai/RL/BaseEnvironment.py
+++ b/freqtrade/freqai/RL/BaseEnvironment.py
@@ -165,12 +165,12 @@ class BaseEnvironment(gym.Env):
         if self._position == Positions.Neutral:
             return 0.
         elif self._position == Positions.Short:
-            current_price = self.add_entry_fee(self.prices.iloc[self._current_tick].open)
-            last_trade_price = self.add_exit_fee(self.prices.iloc[self._last_trade_tick].open)
-            return (last_trade_price - current_price) / last_trade_price
-        elif self._position == Positions.Long:
             current_price = self.add_exit_fee(self.prices.iloc[self._current_tick].open)
             last_trade_price = self.add_entry_fee(self.prices.iloc[self._last_trade_tick].open)
+            return (last_trade_price - current_price) / last_trade_price
+        elif self._position == Positions.Long:
+            current_price = self.add_entry_fee(self.prices.iloc[self._current_tick].open)
+            last_trade_price = self.add_exit_fee(self.prices.iloc[self._last_trade_tick].open)
             return (current_price - last_trade_price) / last_trade_price
         else:
             return 0.
@@ -210,9 +210,8 @@ class BaseEnvironment(gym.Env):
         """
         An example reward function. This is the one function that users will likely
         wish to inject their own creativity into.
-        :params:
-        action: int = The action made by the agent for the current candle.
-        :returns:
+        :param action: int = The action made by the agent for the current candle.
+        :return:
         float = the reward to give to the agent for current step (used for optimization
             of weights in NN)
         """
@@ -234,7 +233,7 @@ class BaseEnvironment(gym.Env):
     def _update_total_profit(self):
         pnl = self.get_unrealized_profit()
         if self.compound_trades:
-            # assumes unite stake and compounding
+            # assumes unitestake and compounding
             self._total_profit = self._total_profit * (1 + pnl)
         else:
             # assumes unit stake and no compounding
diff --git a/freqtrade/freqai/RL/BaseReinforcementLearningModel.py b/freqtrade/freqai/RL/BaseReinforcementLearningModel.py
index 885918ffb..85756ad8f 100644
--- a/freqtrade/freqai/RL/BaseReinforcementLearningModel.py
+++ b/freqtrade/freqai/RL/BaseReinforcementLearningModel.py
@@ -180,17 +180,12 @@ class BaseReinforcementLearningModel(IFreqaiModel):
                 if self.data_provider._exchange is None:  # type: ignore
                     logger.error('No exchange available.')
                 else:
-                    current_value = self.data_provider._exchange.get_rate(  # type: ignore
+                    current_rate = self.data_provider._exchange.get_rate(  # type: ignore
                                 pair, refresh=False, side="exit", is_short=trade.is_short)
-                openrate = trade.open_rate
+
                 now = datetime.now(timezone.utc).timestamp()
-                trade_duration = int((now - trade.open_date.timestamp()) / self.base_tf_seconds)
-                if 'long' in str(trade.enter_tag):
-                    market_side = 1
-                    current_profit = (current_value - openrate) / openrate
-                else:
-                    market_side = 0
-                    current_profit = (openrate - current_value) / openrate
+                trade_duration = int((now - trade.open_date_utc) / self.base_tf_seconds)
+                current_profit = trade.calc_profit_ratio(current_rate)
 
         return market_side, current_profit, int(trade_duration)