fix: add objectives support to NuconGoalEnv; fix README uncertainty example

- NuconGoalEnv now accepts objectives/objective_weights; additive on top
  of the goal reward, same interface as NuconEnv
- README: use UncertaintyPenalty/UncertaintyAbort correctly (via objectives
  and terminators, not as constructor params that don't exist)
- Step 3 prose updated to reference composable callables

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

nucon/rl.py

@@ -280,6 +280,8 @@ class NuconGoalEnv(gym.Env):
         seconds_per_step=5,
         terminators=None,
         terminate_above=0,
+        objectives=None,
+        objective_weights=None,
     ):
         super().__init__()
 
@@ -349,6 +351,9 @@ class NuconGoalEnv(gym.Env):
         self.action_space = spaces.Dict(action_spaces)
 
         self._terminators = terminators or []
+        _objs = objectives or []
+        self._objectives = [Objectives[o] if isinstance(o, str) else o for o in _objs]
+        self._objective_weights = objective_weights or [1.0] * len(self._objectives)
         self._desired_goal = np.zeros(n_goals, dtype=np.float32)
         self._total_steps = 0
 
@@ -410,6 +415,7 @@ class NuconGoalEnv(gym.Env):
         info = {'achieved_goal': obs['achieved_goal'], 'desired_goal': obs['desired_goal'],
                 'obs': obs['observation']}
         reward = float(self.compute_reward(obs['achieved_goal'], obs['desired_goal'], info))
+        reward += sum(w * o(obs['observation']) for o, w in zip(self._objectives, self._objective_weights))
         terminated = any(t(obs['observation']) > self.terminate_above for t in self._terminators)
         truncated = False
         return obs, reward, terminated, truncated, info