Mechanisms for a No-Regret Agent: Beyond the Common Prior

@article{Camara2020MechanismsFA,
  title={Mechanisms for a No-Regret Agent: Beyond the Common Prior},
  author={Modibo K. Camara and Jason D. Hartline and Aleck C. Johnsen},
  journal={2020 IEEE 61st Annual Symposium on Foundations of Computer Science (FOCS)},
  year={2020},
  pages={259-270}
}
A rich class of mechanism design problems can be understood as incomplete-information games between a principal who commits to a policy and an agent who responds, with payoffs determined by an unknown state of the world. Traditionally, these models require strong and often-impractical assumptions about beliefs (a common prior over the state). In this paper, we dispense with the common prior. Instead, we consider a repeated interaction where both the principal and the agent may learn over time… 
Learning to Persuade on the Fly: Robustness Against Ignorance
TLDR
This work studies a repeated persuasion setting between a sender and a receiver, where at each time t, the sender shares information about a payoff-relevant state with the receiver, and subsequent to receiving information about it, the receiver chooses an action from a finite set.
MACHINE LEARNING FOR STRATEGIC INFERENCE
TLDR
It is shown how Adaptive Boosting algorithms can be specified to induce behavior that is (approximately) as-if rational using only observed data, and in particular without needing to infer the optimal response from Bayes rule.
Machine Learning for Strategic Inference
TLDR
It is shown how Adaptive Boosting algorithms can be specified to induce behavior that is (approximately) as-if rational using only observed data, and in particular without needing to infer the optimal response from Bayes rule.

References

SHOWING 1-10 OF 70 REFERENCES
Simple versus Optimal Contracts
TLDR
This paper considers the classic principal-agent model of contract theory, and proves that linear contracts are guaranteed to be worst-case optimal, ranging over all reward distributions consistent with the given moments.
Econometrics for Learning Agents
TLDR
This paper shows how to infer values of players who use algorithmic learning strategies from observed data in the generalized second price auction, an important first step before moving to testing any learning theoretic behavioral model on auction data.
Bayesian Exploration: Incentivizing Exploration in Bayesian Games
TLDR
The goal is to design a recommendation policy for the principal which respects agents' incentives and minimizes a suitable notion of regret, and shows how the principal can identify (and explore) all explorable actions, and use the revealed information to perform optimally.
Robustness and Linear Contracts
We consider a moral hazard problem where the principal is uncertain as to what the agent can and cannot do: she knows some actions available to the agent, but other, unknown actions may also exist.
A General Class of Adaptive Strategies
We exhibit and characterize an entire class of simple adaptive strategies, in the repeated play of a game, having the Hannan-consistency property: in the long-run, the player is guaranteed an average
Policy Regret in Repeated Games
TLDR
This work focuses on the game theoretic setting, when the adversary is a self-interested agent, and shows that the external regret and policy regret are not in conflict, and that a wide class of algorithms can ensure both as long as an adversary is also using such an algorithm.
Algorithmic Bayesian persuasion
TLDR
This paper examines persuasion through a computational lens, focusing on the celebrated Bayesian persuasion model of Kamenica and Gentzkow, and examines the sender's optimization task in three of the most natural input models for this problem, and essentially pin down its computational complexity in each.
Robust Predictions in Games with Incomplete Information
We analyze games of incomplete information and offer equilibrium predictions which are valid for, and in this sense robust to, all possible private information structures that the agents may have.
...
1
2
3
4
5
...