REVIEW 2 cited by
Follower Agnostic Methods for Stackelberg Games
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Follower Agnostic Methods for Stackelberg Games
read the original abstract
In this paper, we present an efficient algorithm to solve online Stackelberg games, featuring multiple followers, in a follower-agnostic manner. Unlike previous works, our approach works even when leader has no knowledge about the followers' utility functions or strategy space. Our algorithm introduces a unique gradient estimator, leveraging specially designed strategies to probe followers. In a departure from traditional assumptions of optimal play, we model followers' responses using a convergent adaptation rule, allowing for realistic and dynamic interactions. The leader constructs the gradient estimator solely based on observations of followers' actions. We provide both non-asymptotic convergence rates to stationary points of the leader's objective and demonstrate asymptotic convergence to a \emph{local Stackelberg equilibrium}. To validate the effectiveness of our algorithm, we use this algorithm to solve the problem of incentive design on a large-scale transportation network, showcasing its robustness even when the leader lacks access to followers' demand.
Forward citations
Cited by 2 Pith papers
-
Benchmarking Bilevel Derivative-Free Optimization Algorithms
Introduces a refereeing procedure and full computational cost accounting to improve benchmarking fairness for bilevel derivative-free optimization algorithms.
-
Finding a Multiple Follower Stackelberg Equilibrium: A Fully First-Order Method
A first-order Lagrangian penalty method is claimed to reach an ε-stationary multi-follower Stackelberg equilibrium in O(k²ε^{-6-α}) gradient evaluations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.