api: extend reporting Player's end_episode method

examples/eater-usage.py

@@ -49,9 +49,9 @@ class MyPlayer(InformedPlayer):
 
         self._say('Available actions: {}'.format({a.name: a.value for a in Eater.Actions}))
 
-    def end_episode(self):
+    def end_episode(self, outcome: int, alive: bool, success: bool):
         """Method called at the when an episode is completed."""
-        self._say('Episode completed, my reward is {}'.format(self.reward))
+        self._say('Episode completed, my reward is {}'.format(outcome))
 
     # random player
     def play(self, turn: int, percept: Eater.Percept, actions: Iterable[Eater.Actions]) -> Eater.Actions:

wumpus/gridworld.py

@@ -435,8 +435,9 @@ class Player(object):
         """Method called at the beginning of the episode."""
         pass
 
-    def end_episode(self):
-        """Method called at the when an episode is completed."""
+    def end_episode(self, outcome: int, alive: bool, success: bool):
+        """Method called at the when an episode is completed with the outcome of the game and whether the agent was still alive and successfull.
+        """
         pass
 
     def play(self, turn: int, percept: Percept, actions: Iterable[Agent.Actions]) -> Agent.Actions:
@@ -530,7 +531,7 @@ def run_episode(world: GridWorld, agent: Agent, player: Player, horizon: int = 0
     else:
         print('Episode terminated by maximum number of steps ({}).'.format(horizon), file=outf)
 
-    player.end_episode()
+    player.end_episode(agent.reward, agent.isAlive, agent.success)
 
     print(world, file=outf)
     print('Episode terminated with a reward of {} for agent {}'.format(agent.reward, agent.name), file=outf)