Abstract
Policy models often assume that the relationship between a policy instrument and its outcome remains stable across institutional conditions. However, in adaptive socio-technical systems, this assumption may fail: regulatory change can alter incentives, agents can respond strategically, and the mapping from policy variables to aggregate outcomes can change. This paper studies such regime change as a transfer-learning problem in adaptive multi-agent systems.
Policy Regime Modeling
A policy regime is represented as a learning problem induced by an observable input distribution and a target function mapping policy variables to outcomes. We compare a blank-slate learner that searches a flexible hypothesis class in the new regime with a transfer learner whose effective hypothesis class is restricted by structural knowledge from the previous regime.
Effects of Transfer
Transfer is beneficial when this restriction preserves the new target function while reducing effective complexity; it is harmful when the restriction excludes the new target and creates misspecification. A stylized emissions-regulation experimental environment and a dynamic agent-based model (ABM) robustness experiment support this claim.
Experimental Results
When the target regime preserves an affine monotone tax-emissions relation, transfer improves empirical small-sample performance. Conversely, when the target regime introduces a threshold break, the same transferred structure produces negative transfer: held-out error remains high, online prediction generates more mistakes, and repeated online streams show larger cumulative and final-window error under misspecification.
Methodological Contribution
The contribution is methodological: previous regulatory experience should be reused when it captures stable structural invariants, but treated cautiously when policy change alters the policy-outcome relationship.
Blogger's Review: This study provides a profound theoretical framework for transfer learning in adaptive multi-agent systems, emphasizing the complexities and risks of effectively utilizing past experiences in the context of policy change. Understanding the pros and cons of this transfer learning is crucial for policymakers.