Expanding AI technologies in game-theoretic markets creates a 'Poisoned Apple' effect where agents release unused technologies to manipulate regulators into choosing market designs that benefit them at the expense of opponents and fairness.
Bayesian persuasion.American Economic Review, 101(6):2590–2615, 2011
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Introduces structured Stackelberg games and the Stackelberg-Littlestone dimension to characterize the leader's optimal regret and sample complexity when context predicts follower type.
Algorithms achieve O(T^{1/2}) regret in contextual Stackelberg games via reduction to linear contextual bandits, improving on prior O(T^{2/3}) rates.
A safe exploration algorithm learns an unknown receiver bias parameter in repeated information design and achieves O(log log T) regret with a matching lower bound.
In a coordination game with switching costs and logit quantal response, endogenous hard transformations (action deletion) eliminate inertia better than soft ones (taxes), while meta-level antagonistic social preferences can block individually Pareto-improving reforms.
citing papers explorer
-
The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents
Expanding AI technologies in game-theoretic markets creates a 'Poisoned Apple' effect where agents release unused technologies to manipulate regulators into choosing market designs that benefit them at the expense of opponents and fairness.
-
Learning in Structured Stackelberg Games
Introduces structured Stackelberg games and the Stackelberg-Littlestone dimension to characterize the leader's optimal regret and sample complexity when context predicts follower type.
-
Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information
Algorithms achieve O(T^{1/2}) regret in contextual Stackelberg games via reduction to linear contextual bandits, improving on prior O(T^{2/3}) rates.
-
Learning to Persuade a Biased Receiver
A safe exploration algorithm learns an unknown receiver bias parameter in repeated information design and achieves O(log log T) regret with a matching lower bound.
-
Why Efficient Reforms Fail: Endogenous Game Transformation under Status Quo Bias and Social Preferences
In a coordination game with switching costs and logit quantal response, endogenous hard transformations (action deletion) eliminate inertia better than soft ones (taxes), while meta-level antagonistic social preferences can block individually Pareto-improving reforms.