Passivity Tools for Hybrid Learning Rules in Large Populations
Recent work has pioneered the use of system-theoretic passivity to study equilibrium
stability for the dynamics of noncooperative strategic interactions in large populations of …
stability for the dynamics of noncooperative strategic interactions in large populations of …
Can taxes improve congestion on all networks?
We ask if it is possible to positively influence social behavior with no risk of unintentionally
incentivizing pathological behavior. In network routing problems, if network traffic is …
incentivizing pathological behavior. In network routing problems, if network traffic is …
Fundamental limits of locally-computed incentives in network routing
We ask if it is possible to positively influence social behavior with no risk of unintentionally
incentivizing pathological behavior. In network routing problems, if network traffic is …
incentivizing pathological behavior. In network routing problems, if network traffic is …
Demand-independent optimal tolls
Wardrop equilibria in nonatomic congestion games are in general inefficient as they do not
induce an optimal flow that minimizes the total travel time. Network tolls are a prominent and …
induce an optimal flow that minimizes the total travel time. Network tolls are a prominent and …
Learnability of edge cost functions in routing games
We study the learnability of the edge cost functions in routing games from observations of
the equilibrium flows, where the learnability is measured as the minimum number of …
the equilibrium flows, where the learnability is measured as the minimum number of …
Demand-independent tolls
Wardrop equilibria in nonatomic congestion games are in general inefficient as they do not
induce an optimal flow that minimizes the total travel time. Network tolls are a prominent and …
induce an optimal flow that minimizes the total travel time. Network tolls are a prominent and …
[PDF][PDF] A Systems Theoretic Perspective of the Outer Alignment Problem
D Gossman, H Kannan - 2023 - easychair.org
The problem of ensuring that an artificial intelligence (AI) system's objectives and actions
match the intended outcome is known as the problem of alignment. Alignment can be …
match the intended outcome is known as the problem of alignment. Alignment can be …
[图书][B] On learning Game-Theoretical models with Application to Urban Mobility
J Thai - 2017 - search.proquest.com
Modeling real-world processes as convex optimization or variational inequality problems is
a common practice as it enables to leverage powerful mathematical tools for the study of …
a common practice as it enables to leverage powerful mathematical tools for the study of …
Designing for Emergent Security in Heterogeneous Human-Machine teams
PN Brown - 2019 IEEE 58th Conference on Decision and …, 2019 - ieeexplore.ieee.org
This work seeks to design decisionmaking rules for autonomous agents to jointly influence
and optimize the behavior of teamed human decisionmakers in the presence of an …
and optimize the behavior of teamed human decisionmakers in the presence of an …
[图书][B] Robust Methods for Inuencing Strategic Behavior
PN Brown - 2018 - search.proquest.com
Today's world contains many examples of engineered systems that are tightly coupled with
their users and customers. In these settings, the strategic and economic behavior of users …
their users and customers. In these settings, the strategic and economic behavior of users …