Search Results for author: Mirco Musolesi

Found 24 papers, 4 papers with code

Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning

no code implementations20 Jan 2023 Elizaveta Tennant, Stephen Hailes, Mirco Musolesi

In particular, we believe that an interesting and insightful starting point is the analysis of emergent behavior of Reinforcement Learning (RL) agents that act according to a predefined set of moral rewards in social dilemmas.

Multi-agent Reinforcement Learning reinforcement-learning +1

Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systems

no code implementations19 Jan 2023 Nayana Dasgupta, Mirco Musolesi

Direct punishment is an ubiquitous social mechanism that has been shown to benefit the emergence of cooperation within the natural world, however no prior work has investigated its impact on populations of learning agents.

Multi-agent Reinforcement Learning Navigate

CT-DQN: Control-Tutored Deep Reinforcement Learning

no code implementations2 Dec 2022 Francesco De Lellis, Marco Coraggio, Giovanni Russo, Mirco Musolesi, Mario di Bernardo

One of the major challenges in Deep Reinforcement Learning for control is the need for extensive training to learn the policy.

Car Racing OpenAI Gym +2

Graph Neural Modeling of Network Flows

no code implementations12 Sep 2022 Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

The widely-used objective that we focus on is the maximum utilization of any link in the network, given traffic demands and a routing strategy.

Graph Learning

Trust-based Consensus in Multi-Agent Reinforcement Learning Systems

no code implementations25 May 2022 Ho Long Fung, Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

An often neglected issue in multi-agent reinforcement learning (MARL) is the potential presence of unreliable agents in the environment whose deviations from expected behavior can prevent a system from accomplishing its intended tasks.

Multi-agent Reinforcement Learning reinforcement-learning +1

DeepCreativity: Measuring Creativity with Deep Learning Techniques

no code implementations16 Jan 2022 Giorgio Franceschelli, Mirco Musolesi

Measuring machine creativity is one of the most fascinating challenges in Artificial Intelligence.

Solving Graph-based Public Goods Games with Tree Search and Imitation Learning

1 code implementation NeurIPS 2021 Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

In particular, we define a Markov Decision Process which incrementally generates an mIS, and adopt a planning method to search for equilibria, outperforming existing methods.

Combinatorial Optimization Imitation Learning

Reinforcement Learning on Encrypted Data

no code implementations16 Sep 2021 Alberto Jesu, Victor-Alexandru Darvariu, Alessandro Staffolani, Rebecca Montanari, Mirco Musolesi

The growing number of applications of Reinforcement Learning (RL) in real-world domains has led to the development of privacy-preserving techniques due to the inherently sensitive nature of data.

Privacy Preserving reinforcement-learning +1

Solving Graph-based Public Good Games with Tree Search and Imitation Learning

1 code implementation12 Jun 2021 Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

Public goods games represent insightful settings for studying incentives for individual agents to make contributions that, while costly for each of them, benefit the wider society.

Combinatorial Optimization Imitation Learning

Planning Spatial Networks with Monte Carlo Tree Search

no code implementations12 Jun 2021 Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

We tackle the problem of goal-directed graph construction: given a starting graph, a budget of modifications, and a global objective function, the aim is to find a set of edges whose addition to the graph achieves the maximum improvement in the objective (e. g., communication efficiency).

graph construction

Copyright in Generative Deep Learning

no code implementations19 May 2021 Giorgio Franceschelli, Mirco Musolesi

In this article, we consider a set of key questions in the area of generative deep learning for the arts, including the following: is it possible to use copyrighted works as training set for generative models?

Code Generation

Creativity and Machine Learning: A Survey

no code implementations6 Apr 2021 Giorgio Franceschelli, Mirco Musolesi

There is a growing interest in the area of machine learning and creativity.

BIG-bench Machine Learning

Cooperation and Reputation Dynamics with Reinforcement Learning

no code implementations15 Feb 2021 Nicolas Anastassacos, Julian García, Stephen Hailes, Mirco Musolesi

We use a simple model of reinforcement learning to show that reputation mechanisms generate two coordination problems: agents need to learn how to coordinate on the meaning of existing reputations and collectively agree on a social norm to assign reputations to others based on their behavior.

Q-Learning reinforcement-learning +1

Modelling Grocery Retail Topic Distributions: Evaluation, Interpretability and Stability

no code implementations4 May 2020 Mariflor Vega-Carrasco, Jason O'sullivan, Rosie Prior, Ioanna Manolopoulou, Mirco Musolesi

Our approach is an alternative to standard label-switching techniques and provides a single posterior summary set of topics, as well as associated measures of uncertainty.

Topic Models

Goal-directed graph construction using reinforcement learning

1 code implementation30 Jan 2020 Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

In this work, we formulate the construction of a graph as a decision-making process in which a central agent creates topologies by trial and error and receives rewards proportional to the value of the target objective.

Decision Making graph construction +2

Graph Input Representations for Machine Learning Applications in Urban Network Analysis

no code implementations11 Dec 2019 Alessio Pagani, Abhinav Mehrotra, Mirco Musolesi

In this paper, we design and evaluate six different graph input representations (i. e., representations of the network paths), by considering the network's topological and temporal characteristics, for being used as inputs for machine learning models to learn the behavior of urban networks paths.

BIG-bench Machine Learning

Learning through Probing: a decentralized reinforcement learning architecture for social dilemmas

no code implementations26 Sep 2018 Nicolas Anastassacos, Mirco Musolesi

Using social dilemmas as the training ground, we present a novel learning architecture, Learning through Probing (LTP), where agents utilize a probing mechanism to incorporate how their opponent's behavior changes when an agent takes an action.

Multi-agent Reinforcement Learning Q-Learning +2

You are your Metadata: Identification and Obfuscation of Social Media Users using Metadata Information

no code implementations27 Mar 2018 Beatrice Perez, Mirco Musolesi, Gianluca Stringhini

Metadata are associated to most of the information we produce in our daily interactions and communication in the digital world.


Towards Deep Learning Models for Psychological State Prediction using Smartphone Data: Challenges and Opportunities

no code implementations16 Nov 2017 Gatis Mikelsons, Matthew Smith, Abhinav Mehrotra, Mirco Musolesi

We characterize the mobility patterns of individuals using the GPS metrics presented in the literature and employ these metrics as input to the network.

BIG-bench Machine Learning

Interpretable Machine Learning for Privacy-Preserving Pervasive Systems

no code implementations23 Oct 2017 Benjamin Baron, Mirco Musolesi

Our everyday interactions with pervasive systems generate traces that capture various aspects of human behavior and enable machine learning algorithms to extract latent information about users.

BIG-bench Machine Learning Interpretable Machine Learning +1

Probabilistic Matching: Causal Inference under Measurement Errors

no code implementations13 Mar 2017 Fani Tsapeli, Peter Tino, Mirco Musolesi

The abundance of data produced daily from large variety of sources has boosted the need of novel approaches on causal inference analysis from observational data.

Causal Inference

Kissing Cuisines: Exploring Worldwide Culinary Habits on the Web

no code implementations26 Oct 2016 Sina Sajadmanesh, Sina Jafarzadeh, Seyed Ali Osia, Hamid R. Rabiee, Hamed Haddadi, Yelena Mejova, Mirco Musolesi, Emiliano De Cristofaro, Gianluca Stringhini

In this paper, we present a large-scale study of recipes published on the web and their content, aiming to understand cuisines and culinary habits around the world.


Cannot find the paper you are looking for? You can Submit a new open access paper.