humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909687286333440 |
|---|---|
| author | Nazarov, Rodion Quinn, Anthony Shorten, Robert Marecek, Jakub |
| author_facet | Nazarov, Rodion Quinn, Anthony Shorten, Robert Marecek, Jakub |
| contents | Artificial intelligence (AI) systems often interact with multiple agents. The regulation of such AI systems often requires that {\em a priori\/} guarantees of fairness and robustness be satisfied. With stochastic models of agents' responses to the outputs of AI systems, such {\em a priori\/} guarantees require non-trivial reasoning about the corresponding stochastic systems. Here, we present an open-source PyTorch-based toolkit for the use of stochastic control techniques in modelling interconnections of AI systems and properties of their repeated uses. It models robustness and fairness desiderata in a closed-loop fashion, and provides {\em a priori\/} guarantees for these interconnections. The PyTorch-based toolkit removes much of the complexity associated with the provision of fairness guarantees for closed-loop models of multi-agent systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09626 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems Nazarov, Rodion Quinn, Anthony Shorten, Robert Marecek, Jakub Artificial Intelligence Systems and Control Artificial intelligence (AI) systems often interact with multiple agents. The regulation of such AI systems often requires that {\em a priori\/} guarantees of fairness and robustness be satisfied. With stochastic models of agents' responses to the outputs of AI systems, such {\em a priori\/} guarantees require non-trivial reasoning about the corresponding stochastic systems. Here, we present an open-source PyTorch-based toolkit for the use of stochastic control techniques in modelling interconnections of AI systems and properties of their repeated uses. It models robustness and fairness desiderata in a closed-loop fashion, and provides {\em a priori\/} guarantees for these interconnections. The PyTorch-based toolkit removes much of the complexity associated with the provision of fairness guarantees for closed-loop models of multi-agent systems. |
| title | humancompatible.interconnect: Testing Properties of Repeated Uses of Interconnections of AI Systems |
| topic | Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2507.09626 |