Search Results for author:
Found 45 papers, 2 papers with code
Learning Adversarial MDPs with Stochastic Hard Constraints
To the best of our knowledge, our work is the first to study CMDPs involving both adversarial losses and hard constraints.
Markov Persuasion Processes: Learning to Persuade from Scratch
Recently, Markov persuasion processes (MPPs) have been introduced to capture sequential scenarios where a sender faces a stream of myopic receivers in a Markovian environment.
$(ε, u)$-Adaptive Regret Minimization in Heavy-Tailed Bandits
In this setting, we study the regret minimization problem when $\epsilon$ and $u$ are unknown to the learner and it has to adapt.
Learning Optimal Contracts: How to Exploit Small Action Spaces
We design an algorithm that learns an approximately-optimal contract with high probability in a number of rounds polynomial in the size of the outcome space, when the number of actions is constant.
A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints
We study online learning in episodic constrained Markov decision processes (CMDPs), where the goal of the learner is to collect as much reward as possible over the episodes, while guaranteeing that some long-term constraints are satisfied during the learning process.
Autoregressive Bandits
Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing.
Dynamic Pricing with Volume Discounts in Online Settings
We ran a real-world 4-month-long A/B testing experiment in collaboration with an Italian e-commerce company, in which our algorithm PVD-B-corresponding to A configuration-has been compared with human pricing specialists-corresponding to B configuration.
A Unifying Framework for Online Optimization with Long-Term Constraints
We present the first best-of-both-world type algorithm for this general class of problems, with no-regret guarantees both in the case in which rewards and constraints are selected according to an unknown stochastic model, and in the case in which they are selected at each round by an adversary.
Sequential Information Design: Learning to Persuade in the Dark
At each round, the sender observes the realizations of random events in the SDM problem.
A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving
This work shows that we can recover from this weakness by bridging the gap between sequential adversarial team games and 2-player games.
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts
We provide two algorithms to address TP-MAB problems, namely, TP-UCB-FR and TP-UCB-EW, which exploit the partial information disclosed by the reward collected over time.
Public Information Representation for Adversarial Team Games
Interestingly, we show that our game is more expressive than the original extensive-form game as any state/action abstraction of the extensive-form game can be captured by our representation, while the reverse does not hold.
Safe Online Bid Optimization with Return-On-Investment and Budget Constraints subject to Uncertainty
More interestingly, we provide an algorithm, namely GCB_{safe}(\psi,\phi), guaranteeing both sublinear pseudo-regret and safety w. h. p.
Exploiting Opponents Under Utility Constraints in Sequential Games
Recently, game-playing agents based on AI techniques have demonstrated super-human performance in several sequential games, such as chess, Go, and poker.
Multi-Receiver Online Bayesian Persuasion
Then, we focus on the case of submodular sender's utility functions and we show that, in this case, it is possible to design a polynomial-time no-$(1 - \frac{1}{e})$-regret algorithm.
Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
The existence of simple uncoupled no-regret learning dynamics that converge to correlated equilibria in normal-form games is a celebrated result in the theory of multi-agent systems.
Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies
Team members can coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game.
Trembling-Hand Perfection and Correlation in Sequential Games
After providing an axiomatic definition of EFPCE, we show that one always exists since any perfect (Nash) equilibrium constitutes an EFPCE, and that it is a refinement of EFCE, as any EFPCE is also an EFCE.
Computer Science and Game Theory
Online Posted Pricing with Unknown Time-Discounted Valuations
We evaluate our mechanisms in terms of competitive ratio, measuring the worst-case ratio between their revenue and that of an optimal mechanism that knows the distribution of valuations.
Computer Science and Game Theory
Persuading Voters in District-based Elections
We study both private signaling, in which the sender can use a private communication channel per receiver, and public signaling, in which the sender can use a single communication channel for all the receivers.
Online Bayesian Persuasion
We are interested in no-regret algorithms prescribing a signaling scheme at each round of the repeated interaction with performances close to that of the best-in-hindsight signaling scheme.
Faster Algorithms for Optimal Ex-Ante Coordinated Collusive Strategies in Extensive-Form Zero-Sum Games
Second, we provide an algorithm that computes such an optimal distribution by only using profiles where only one of the team members gets to randomize in each profile.
No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
When each player has low trigger regret, the empirical frequency of play is close to an EFCE.
Online Joint Bid/Daily Budget Optimization of Internet Advertising Campaigns
We experimentally evaluate our algorithms with synthetic settings generated from real data from Yahoo!, and we present the results of the adoption of our algorithms in a real-world application with a daily average spent of 1, 000 Euros for more than one year.
Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry
A natural question is the following: is it possible for an informed sender to reduce the overall social cost via the strategic provision of information to players who update their beliefs rationally?
Public Bayesian Persuasion: Being Almost Optimal and Almost Persuasive
Unlike prior works on this problem, we study the public persuasion problem in the general setting with: (i) arbitrary state spaces; (ii) arbitrary action spaces; (iii) arbitrary sender's utility functions.
Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning
Many real-world applications involve teams of agents that have to coordinate their actions to reach a common goal against potential adversaries.
Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces
As a result, solving these games begets the challenge of designing learning algorithms that can find (approximate) equilibria with high confidence, using as few simulator queries as possible.
Election Manipulation on Social Networks: Seeding, Edge Removal, Edge Addition
We focus on the election manipulation problem through social influence, where a manipulator exploits a social network to make her most preferred candidate win an election.
Learning to Correlate in Multi-Player General-Sum Sequential Games
In the context of multi-player, general-sum games, there is an increasing interest in solution concepts modeling some form of communication among players, since they can lead to socially better outcomes with respect to Nash equilibria, and may be reached through learning dynamics in a decentralized fashion.
Computer Science and Game Theory
Persuading Voters: It's Easy to Whisper, It's Hard to Speak Loud
In the former, we show that an optimal signaling scheme can be computed efficiently both under a $k$-voting rule and plurality voting.
Bayesian Persuasion with Sequential Games
After formalizing the notions of ex ante and ex interim persuasiveness (which differ in the time at which the receivers commit to following the sender's signaling scheme), we investigate the continuous optimization problem of computing a signaling scheme which maximizes the sender's expected revenue.
Election Manipulation on Social Networks with Messages on Multiple Candidates
We study the problem of election control through social influence when the manipulator is allowed to use the locations that she acquired on the network for sending \emph{both} positive and negative messages on \emph{multiple} candidates, widely extending the previous results available in the literature that study the influence of a single message on a single candidate.
Computer Science and Game Theory
Computing Optimal Coarse Correlated Equilibria in Sequential Games
We investigate the computation of equilibria in extensive-form games where ex ante correlation is possible, focusing on correlated equilibria requiring the least amount of communication between the players and the mediator.
Practical exact algorithm for trembling-hand equilibrium refinements in games
Nash equilibrium strategies have the known weakness that they do not prescribe rational play in situations that are reached with zero probability according to the strategies themselves, for example, if players have made mistakes.
Ex ante coordination and collusion in zero-sum multi-player extensive-form games
This paper focuses on zero-sum games where a team of players faces an opponent, as is the case, for example, in Bridge, collusion in poker, and many non-recreational applications such as war, where the colluders do not have time or means of communicating during battle, collusion in bidding, where communication during the auction is illegal, and coordinated swindling in public.
Computing the Strategy to Commit to in Polymatrix Games (Extended Version)
We study the computational complexity of finding or approximating an optimistic or pessimistic leader-follower equilibrium in specific classes of succinct games---polymatrix like---which are equivalent to 2-player Bayesian games with uncertainty over the follower, with interdependent or independent types.
Facing Multiple Attacks in Adversarial Patrolling Games with Alarmed Targets
We show that even the error of just a single resource can lead to an arbitrary inefficiency, when the inefficiency is defined as the ratio of the Defender's utilities obtained with a wrong guess and a correct guess.
How to Maximize the Spread of Social Influence: A Survey
This survey presents the main results achieved for the influence maximization problem in social networks.
Computational Results for Extensive-Form Adversarial Team Games
We provide, to the best of our knowledge, the first computational study of extensive-form adversarial team games.
Methods for finding leader--follower equilibria with multiple followers
The concept of leader--follower (or Stackelberg) equilibrium plays a central role in a number of real--world applications of game theory.
Team-maxmin equilibrium: efficiency bounds and algorithms
The Team-maxmin equilibrium prescribes the optimal strategies for a team of rational players sharing the same goal and without the capability of correlating their strategies in strategic games against an adversary.
Unimodal Thompson Sampling for Graph-Structured Arms
We study, to the best of our knowledge, the first Bayesian algorithm for unimodal Multi-Armed Bandit (MAB) problems with graph structure.
Multi-resource defensive strategies for patrolling games with alarm systems
The central problem with an alarm system, unexplored in other Security Games, is finding the best strategy to respond to alarm signals for each mobile defensive resource.
Adversarial patrolling with spatially uncertain alarm signals
That is, the alarm system is able to detect an attack but it is uncertain on the exact position where the attack is taking place.
