Black-Box Lifting and Robustness Theorems for Multi-Agent Contracts

TL;DR

This paper extends multi-agent contract analysis beyond pure Nash equilibria to include mixed and correlated equilibria, showing that complex recommendations offer limited gains and establishing robustness and approximation guarantees for submodular rewards.

Contribution

It introduces black-box lifting and robustness results for multi-agent contracts, connecting PNE guarantees to broader equilibrium concepts, especially for submodular and XOS rewards.

Findings

Complex recommendations yield at most a constant-factor gain for submodular and XOS rewards.

Contracts and PNEs can be transformed to ensure CCEs approximate PNE utility within constant factors.

Poly-time algorithms achieve constant approximations in CCEs for submodular rewards.

Abstract

Multi-agent contract design has largely evaluated contracts through the lens of pure Nash equilibria (PNE). This focus, however, is not without loss: In general, the principal can strictly gain by recommending a complex, possibly correlated, distribution over actions, while preserving incentive compatibility. In this work, we extend the analysis of multi-agent contracts beyond pure Nash equilibria to encompass more general equilibrium notions, including mixed Nash equilibria as well as (coarse-)correlated equilibria (CCE). The latter, in particular, captures the limiting outcome of agents engaged in learning dynamics. Our main result shows that for submodular and, more generally, XOS rewards, such complex recommendations yield at most a constant-factor gain: there exists a contract and a PNE whose utility is within a constant factor of the best CCE achievable by any contract. This provides a black-box lifting: results established against the best PNE automatically apply with respect to the best CCE, with only a constant factor loss. For submodular rewards, we further show how to transform a contract and a PNE of that contract into a new contract such that any of its CCEs gives a constant approximation to the PNE. This yields black-box robustness: up to constant factors, guarantees established for a specific contract and PNE automatically extend to the modified contract and any of its CCEs. We thus expand prior guarantees for multi-agent contracts and lower the barrier to new ones. As an important corollary, we obtain poly-time algorithms for submodular rewards that achieve constant approximations in any CCE, against the best CCE under the best contract. Such worst-case guarantees are provably unattainable for XOS rewards. Finally, we bound the gap between different equilibrium notions for subadditive, supermodular, and general rewards.