Strategizing against Learners in Bayesian Games

  title={Strategizing against Learners in Bayesian Games},
  author={Y. Mansour and Mehryar Mohri and Jon Schneider and Balasubramanian Sivan},
  booktitle={Annual Conference Computational Learning Theory},
We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy, while the other, the optimizer, is a rational utility maximizer. We consider general Bayesian games, where the payoffs of both the optimizer and the learner could depend on the type, which is drawn from a publicly known distribution, but revealed privately to the learner. We address the following questions: (a) what is the bare minimum that the optimizer can guarantee to obtain… 

Online Learning in Supply-Chain Games

We study a repeated game between a supplier and a retailer who want to maximize their respective profits without full knowledge of the problem parameters. After characterizing the uniqueness of the

How and Why to Manipulate Your Own Agent

This paper proposes to view the outcomes of the agents’ dynamics as inducing a “meta-game” between the users, and proposes a general framework to model and analyze these strategic interactions between users of learning agents for general games and analyze the equilibria induced on the users in three classes of games.



On Stackelberg mixed strategies

It is argued that, even though a Stackelberg mixed strategy can also be seen as a subgame perfect Nash equilibrium of a corresponding extensive-form game, there remains significant value in studying it separately.

Approximation hardness of dominating set problems in bounded degree graphs

Subjectivity and Correlation in Randomized Strategies

Strategizing against No-regret Learners

This work studies the optimal game-play for the player against a mean-based no-regret learner who has three actions and shows that the player can get strictly higher than the Stackelberg equilibrium utility.

Selling to a No-Regret Buyer

This work provides a fairly complete characterization of optimal auctions for the seller in this domain and suggests the seller's optimal achievable revenue is characterized by a linear program, and can be unboundedly better than the best truthful auction yet simultaneously unboundingly worse than the expected welfare.

From External to Internal Regret

This paper gives a simple generic reduction that, given an algorithms for the external regret problem, converts it to an efficient online algorithm for the internal regret problem and derives a quantitative regret bound for a very general setting of regret.

Contracts under Moral Hazard and Adverse Selection

In the classical principal-agent problem, a principal must design a contract to incentivize an agent to perform an action on behalf of the principal to prove tight worst-case approximation bounds between a variety of benchmarks of mechanisms for the principal.

Robust Repeated Auctions under Heterogeneous Buyer Behavior

This work designs a simple state-based mechanism that is simultaneously approximately optimal against a k -lookahead buyer for all k, a buyer who is a no-regret learner, and a buyerWho is a policy-regrets learner.

A Randomization Rule for Selecting Forecasts

We propose a randomized strategy for selecting/combining forecasts that is better than the forecasts used to produce it in a sense made precise in this paper. Unlike traditional methods this approach

A decision-theoretic generalization of on-line learning and an application to boosting

The model studied can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting, and it is shown that the multiplicative weight-update Littlestone?Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems.