February, 2021 - ML cube

15 Feb 21

Learning Probably Approximately Correct Maximin Strategies in Games with Infinite Strategy Spaces

Learning Probably Approximately Correct Maximin Strategies in Games with Infinite Strategy Spaces Authors: Alberto Marchesi, Francesco Trovò, Nicola Gatti Conference: AAAI 2021 Abstract: We tackle the problem of learning equilibria in simulationbased games. In such games, the players’ utility functions cannot be described analytically, as they are given through a black-box simulator that can be […]

15 Feb 21

Online Learning in Non-Cooperative Configurable Markov Decision Process

Online Learning in Non-Cooperative Configurable Markov Decision Process Authors: Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, Marcello Restelli Conference: AAAI 2021 Abstract: In the Configurable Markov Decision Processes there are two entities, a Reinforcement Learning agent and a configurator which can modify some parameters of the environment to improve the performance of the agent. What […]

15 Feb 21

Inverse Reinforcement Learning from a Gradient-based Learner

Inverse Reinforcement Learning from a Gradient-based Learner Authors: Giorgia Ramponi, Gianluca Drappo, Marcello Restelli Conference: NeurIPS 2020 Abstract: Inverse Reinforcement Learning addresses the problem of inferring an expert’s reward function from demonstrations. However, in many applications, we not only have access to the expert’s near-optimal behaviour, but we also observe part of her learning process. […]

15 Feb 21

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits Authors: Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric Conference: NeurIPS 2020 Abstract: In the contextual linear bandit setting, algorithms built on the optimism principle fail to exploit the structure of the problem and have been shown to be asymptotically suboptimal. In this paper, we […]

15 Feb 21

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium Authors: Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti Conference: NeurIPS 2020 Abstract: The existence of simple, uncoupled no-regret dynamics that converge to correlated equilibria in normal-form games is a celebrated result in the theory of multi-agent systems. Specifically, it has been known for more than 20 years […]

15 Feb 21

Online Bayesian Persuasion

Online Bayesian Persuasion Authors: Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti Conference: NeurIPS 2020 Abstract: In Bayesian persuasion, an informed sender has to design a signaling scheme that discloses the right amount of information so as to influence the behavior of a self-interested receiver. This kind of strategic interaction is ubiquitous in real economic […]

15 Feb 21

Sequential transfer in reinforcement learning with a generative model

Sequential transfer in reinforcement learning with a generative model Authors: Andrea Tirinzoni, Riccardo Poiani, Marcello Restelli Conference: ICML 2020 Abstract: We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems poses a […]

15 Feb 21

Control frequency adaptation via action persistence in batch reinforcement learning

Control frequency adaptation via action persistence in batch reinforcement learning Authors: Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli Conference: ICML 2020 Abstract: The choice of the control frequency of a system has a relevant impact on the ability of reinforcement learning algorithms to learn a highly performing policy. In this paper, […]

15 Feb 21

Driving exploration by maximum distribution in gaussian process bandits

Driving exploration by maximum distribution in gaussian process bandits Authors: Alessandro Nuara, Francesco Trovò, Dominic Crippa, Nicola Gatti, Marcello Restelli Conference: AAMAS 2020 Abstract: The problem of finding optimal solutions of stochastic functions over continuous domains is common in several real-world applications, such as, e.g., advertisement allocation, dynamic pricing, and power control in wireless networks. […]

15 Feb 21

Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces

Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces Authors: Alberto Marchesi, Francesco Trovò, Nicola Gatti Conference: AAMAS 2020 Abstract: We tackle the problem of learning equilibria in simulation-based games. In such games, the players’ utility functions cannot be described analytically, as they are given through a black-box simulator that can […]