PreferencePairScenario
Training scenarios · Implementation: mlsysim/engine/scenario_definitions/training.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
Log-probability sums over a preferred and a dispreferred record’s selected tokens.
Notes
Equation: Composition of mlsysim.solvers.PreferencePairModel.solve.
Assumptions: Inputs are routed to PreferencePairModel.solve; their documented regimes and units apply to this configuration.
Excludes: Additional mechanisms beyond the linked solver contracts; the scenario does not collect measurements.
References
Derivation: This scenario binds named inputs to PreferencePairModel. The linked solver contracts own equations, sources, and result-unit definitions.
Examples
Evaluate the named configuration and display a modeled result.
>>> from mlsysim import Scenarios
>>> case = Scenarios.RepairPreferencePair
>>> value = case.result.loss
>>> print(f"{value:.3g}")
0.437Attributes
| Name | Description |
|---|---|
| beta | |
| policy_dispreferred | |
| policy_preferred | |
| reference_dispreferred | |
| reference_preferred | |
| result | Evaluate the stated preference pair case through PreferencePairModel.solve; returns its typed result and quantity units. |
policy_preferred
Type: float.
Declared default: required.
reference_preferred
Type: float.
Declared default: required.
policy_dispreferred
Type: float.
Declared default: required.
reference_dispreferred
Type: float.
Declared default: required.
beta
Type: float.
Declared default: required.
result
engine.scenario_types.PreferencePairScenario.result
Evaluate the stated preference pair case through PreferencePairModel.solve; returns its typed result and quantity units.
Calculation: mlsysim.solvers.PreferencePairModel.solve.