no code implementations • 6 Mar 2024 • Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
To the best of our knowledge, our work is the first to study CMDPs involving both adversarial losses and hard constraints.
no code implementations • 5 Feb 2024 • Francesco Bacchiocchi, Francesco Emanuele Stradi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
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.
no code implementations • 18 Sep 2023 • Francesco Bacchiocchi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
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.
no code implementations • 27 Apr 2023 • Jacopo Germano, Francesco Emanuele Stradi, Gianmarco Genalti, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti
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.
no code implementations • 15 Sep 2022 • Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Giulia Romano, Nicola Gatti
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.
no code implementations • 8 Sep 2022 • Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovo
At each round, the sender observes the realizations of random events in the SDM problem.
no code implementations • NeurIPS 2021 • Martino Bernasconi-de-Luca, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Alberto Marchesi, Francesco Trovò
Recently, game-playing agents based on AI techniques have demonstrated super-human performance in several sequential games, such as chess, Go, and poker.
no code implementations • 11 Jun 2021 • Matteo Castiglioni, Alberto Marchesi, Andrea Celli, Nicola Gatti
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.
no code implementations • 4 Apr 2021 • Gabriele Farina, Andrea Celli, Alberto Marchesi, Nicola Gatti
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.
no code implementations • 11 Dec 2020 • Alberto Marchesi, Nicola Gatti
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
no code implementations • 10 Dec 2020 • Giulia Romano, Gianluca Tartaglia, Alberto Marchesi, Nicola Gatti
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
no code implementations • NeurIPS 2020 • Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
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.
no code implementations • NeurIPS 2020 • Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti
When each player has low trigger regret, the empirical frequency of play is close to an EFCE.
no code implementations • 12 Feb 2020 • Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
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?
no code implementations • 18 Nov 2019 • Alberto Marchesi, Francesco Trovò, Nicola Gatti
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.
1 code implementation • NeurIPS 2019 • Andrea Celli, Alberto Marchesi, Tommaso Bianchi, Nicola Gatti
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
no code implementations • 31 Jul 2018 • Giuseppe De Nittis, Alberto Marchesi, Nicola Gatti
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.