What question did this study set out to answer?

The research aims to explore how unobservable penalties influence gaming strategies in multi-agent reinforcement learning (MARL).

March 21, 2026Open Access

Protocol 3 Preregistration: Enforcement Opacity and the Limits of Regulatory Constraint Design

Key Points

The research aims to explore how unobservable penalties influence gaming strategies in multi-agent reinforcement learning (MARL).
Tested conditions include unconstrained control, stochastic penalty, and hidden schedule.
Penalty schedule secured using SHA-256 before experiments.
Part of the longer Delta-Variable Theory research program.
Hidden penalty schedules disrupt virtue theater strategies identified earlier.
Modalities of penalty exposure yield varying impacts on agent behavior.

Abstract

Protocol 3 of the Constraint-Ethics-Necessity MARL research program. Tests whether epistemic opacity in enforcement — specifically, a hidden penalty schedule unobservable to agents — disrupts the virtue theater gaming strategy identified in Protocol 2. Three conditions: unconstrained control, stochastic penalty (3A), and hidden schedule (3B). Penalty schedule locked via SHA-256 prior to experimental runs. Part of the Delta-Variable Theory research program. Parent study: 10.5281/zenodo.18929040

Protocol 3 Preregistration: Enforcement Opacity and the Limits of Regulatory Constraint Design

Key Points

Abstract

Cite This Study