Zobrazeno 1 - 10
of 15 070
pro vyhledávání: '"Castiglioni, A."'
Autor:
Bacchiocchi, Francesco, Bollini, Matteo, Castiglioni, Matteo, Marchesi, Alberto, Gatti, Nicola
We study online Bayesian persuasion problems in which an informed sender repeatedly faces a receiver with the goal of influencing their behavior through the provision of payoff-relevant information. Previous works assume that the sender has knowledge
Externí odkaz:
http://arxiv.org/abs/2411.06141
We investigate the role of constraints in the computational complexity of min-max optimization. The work of Daskalakis, Skoulakis, and Zampetakis [2021] was the first to study min-max optimization through the lens of computational complexity, showing
Externí odkaz:
http://arxiv.org/abs/2411.03248
Autor:
Bollini, Matteo, Bacchiocchi, Francesco, Castiglioni, Matteo, Marchesi, Alberto, Gatti, Nicola
We study principal-agent problems where a farsighted agent takes costly actions in an MDP. The core challenge in these settings is that agent's actions are hidden to the principal, who can only observe their outcomes, namely state transitions and the
Externí odkaz:
http://arxiv.org/abs/2410.13520
Framing plays a central role in the evaluation of Wilson loops in theories with Chern-Simons actions. In pure Chern-Simons theory, it guarantees topological invariance, while in theories with matter like ABJ(M), our theory of interest, it is essentia
Externí odkaz:
http://arxiv.org/abs/2410.10970
We study online learning in \emph{constrained MDPs} (CMDPs), focusing on the goal of attaining sublinear strong regret and strong cumulative constraint violation. Differently from their standard (weak) counterparts, these metrics do not allow negativ
Externí odkaz:
http://arxiv.org/abs/2410.02275
Autor:
Stradi, Francesco Emanuele, Lunghi, Anna, Castiglioni, Matteo, Marchesi, Alberto, Gatti, Nicola
We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-worlds algorithm able to seamles
Externí odkaz:
http://arxiv.org/abs/2410.02269
Autor:
Genalti, Gianmarco, Mussi, Marco, Gatti, Nicola, Restelli, Marcello, Castiglioni, Matteo, Metelli, Alberto Maria
Rested and Restless Bandits are two well-known bandit settings that are useful to model real-world sequential decision-making problems in which the expected reward of an arm evolves over time due to the actions we perform or due to the nature. In thi
Externí odkaz:
http://arxiv.org/abs/2409.05980
Autor:
Castiglioni, Matteo, Chen, Junjie
In this paper, we initiate the computational problem of jointly designing information and contracts. We consider three possible classes of contracts with decreasing flexibility and increasing simplicity: ambiguous contracts, menus of explicit contrac
Externí odkaz:
http://arxiv.org/abs/2407.05459
Bilateral trade models the problem of facilitating trades between a seller and a buyer having private valuations for the item being sold. In the online version of the problem, the learner faces a new seller and buyer at each time step, and has to pos
Externí odkaz:
http://arxiv.org/abs/2405.18183
We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is to design best-of-both-worlds algorithms that perform optimally under b
Externí odkaz:
http://arxiv.org/abs/2405.16118