style: black format

scripts/plot.py

@@ -46,12 +46,14 @@ def read_metrics(filename: str) -> pd.DataFrame:
                 line,
             ).groups()
 
-            data.append({
-                "episode": int(episode),
-                "winning_rate": float(winning_rate),
-                "mean_score": float(mean_score),
-                "max_tile": int(max_tile),
-            })
+            data.append(
+                {
+                    "episode": int(episode),
+                    "winning_rate": float(winning_rate),
+                    "mean_score": float(mean_score),
+                    "max_tile": int(max_tile),
+                }
+            )
 
     return pd.DataFrame(data)
 

src/gymnasium_2048/agents/ntuple/policy.py

@@ -96,9 +96,9 @@ def predict(self, state: np.ndarray) -> int:
         :param state: The board state.
         :return: Next action to play.
         """
-        return np.argmax([
-            self.evaluate(state=state, action=action) for action in range(4)
-        ])
+        return np.argmax(
+            [self.evaluate(state=state, action=action) for action in range(4)]
+        )
 
     @abstractmethod
     def save(self, path: str | pathlib.Path | io.BufferedIOBase) -> None:
@@ -207,9 +207,9 @@ def learn(
         after_state_tuples = self._get_tuples(state=after_state)
         after_state_value = self.net.predict(tuples=after_state_tuples)
 
-        next_action = np.argmax([
-            self.evaluate(state=next_state, action=a) for a in range(4)
-        ])
+        next_action = np.argmax(
+            [self.evaluate(state=next_state, action=a) for a in range(4)]
+        )
         next_after_state, next_reward, is_legal = TwentyFortyEightEnv.apply_action(
             board=next_state,
             action=next_action,