
TL;DR
This paper develops mechanisms to address adverse selection and moral hazard in multi-agent projects, enabling truthful reporting and efficient collaboration despite hidden actions and private information.
Contribution
It introduces mechanisms that ensure truthful revelation of agents' private information and approximate efficiency, applicable to complex multi-agent dynamic settings.
Findings
Mechanism for truthful capability and chance event revelation
Collusion-resistant mechanism with approximate efficiency
Applicable to diverse multi-agent project scenarios
Abstract
Our goal is to solve both problems of adverse selection and moral hazard for multi-agent projects. In our model, each selected agent can work according to his private "capability tree". This means a process involving hidden actions, hidden chance events and hidden costs in a dynamic manner, and providing contractible consequences which are affecting each other's working process and the outcome of the project. We will construct a mechanism that induces truthful revelation of the agents' capability trees and chance events and to follow the instructions about their hidden decisions. This enables the planner to select the optimal subset of agents and obtain the efficient joint execution. We will construct another mechanism that is collusion-resistant but implements an only approximately efficient outcome. The latter mechanism is widely applicable, and the major application details will be…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Semantic Web and Ontologies · Logic, Reasoning, and Knowledge
