dodox/NuCon
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

rename: objectives -> additional_objectives in NuconGoalEnv

Browse Source 
Clarifies that the goal reward is the primary built-in objective;
additional_objectives are additive on top of it.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Dominik Moritz Roth 2026-03-12 18:56:34 +01:00
parent 36a33e74e5
commit 041e0ec1bd
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -214,7 +214,7 @@ env = NuconGoalEnv(
# Keep policy within the simulator's known data distribution. # Keep policy within the simulator's known data distribution.
# SIM_UNCERTAINTY (kNN-GP posterior std) is injected into obs when a simulator is active. # SIM_UNCERTAINTY (kNN-GP posterior std) is injected into obs when a simulator is active.
# Tune start/scale/threshold to taste. # Tune start/scale/threshold to taste.
objectives=[UncertaintyPenalty(start=0.3, scale=1.0)], # L2 penalty above soft threshold additional_objectives=[UncertaintyPenalty(start=0.3, scale=1.0)], # L2 penalty above soft threshold
terminators=[UncertaintyAbort(threshold=0.7)], # abort episode at hard threshold terminators=[UncertaintyAbort(threshold=0.7)], # abort episode at hard threshold
) )
# Or use a preset: env = gym.make('Nucon-goal_power-v0', simulator=simulator) # Or use a preset: env = gym.make('Nucon-goal_power-v0', simulator=simulator)

8
nucon/rl.py
View File

@ -280,8 +280,8 @@ class NuconGoalEnv(gym.Env):
seconds_per_step=5, seconds_per_step=5,
terminators=None, terminators=None,
terminate_above=0, terminate_above=0,
objectives=None, additional_objectives=None,
objective_weights=None, additional_objective_weights=None,
): ):
super().__init__() super().__init__()
@ -351,9 +351,9 @@ class NuconGoalEnv(gym.Env):
self.action_space = spaces.Dict(action_spaces) self.action_space = spaces.Dict(action_spaces)
self._terminators = terminators or [] self._terminators = terminators or []
_objs = objectives or [] _objs = additional_objectives or []
self._objectives = [Objectives[o] if isinstance(o, str) else o for o in _objs] 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._objective_weights = additional_objective_weights or [1.0] * len(self._objectives)
self._desired_goal = np.zeros(n_goals, dtype=np.float32) self._desired_goal = np.zeros(n_goals, dtype=np.float32)
self._total_steps = 0 self._total_steps = 0