no code implementations • 9 Apr 2024 • Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi
Graphs are a natural representation for systems based on relations between connected entities.
no code implementations • 7 Mar 2024 • Elizaveta Tennant, Stephen Hailes, Mirco Musolesi
In multi-agent (social) environments, complex population-level phenomena may emerge from interactions between individual learning agents.
no code implementations • 21 Jan 2024 • Charles Westphal, Stephen Hailes, Mirco Musolesi
Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL).
no code implementations • 4 Dec 2023 • Elizaveta Tennant, Stephen Hailes, Mirco Musolesi
In particular, we present three case studies of recent works which use learning from experience (i. e., Reinforcement Learning) to explicitly provide moral principles to learning agents - either as intrinsic rewards, moral logical constraints or textual principles for language models.
no code implementations • 20 Oct 2023 • Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi
Identifying causal structure is central to many fields ranging from strategic decision-making to biology and economics.
2 code implementations • 20 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
no code implementations • 12 Sep 2022 • Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi
Network flow problems, which involve distributing traffic such that the underlying infrastructure is used effectively, are ubiquitous in transportation and logistics.
1 code implementation • 26 May 2022 • Christoffel Doorman, Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi
A key problem in network theory is how to reconfigure a graph in order to optimize a quantifiable objective.
no code implementations • 25 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
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.
1 code implementation • 12 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.
no code implementations • 12 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).
no code implementations • 15 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.
no code implementations • 27 May 2020 • Nilufer Tuptuk, Stephen Hailes
In this paper we propose a novel methodology to assist in identifying vulnerabilities in a real-world complex heterogeneous industrial control systems (ICS) using two evolutionary multiobjective optimisation (EMO) algorithms, NSGA-II and SPEA2.
1 code implementation • 30 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.
no code implementations • 8 Feb 2019 • Nicolas Anastassacos, Stephen Hailes, Mirco Musolesi
Social dilemmas have been widely studied to explain how humans are able to cooperate in society.
no code implementations • 22 Nov 2018 • Kehinde Owoeye, Stephen Hailes
Learning the activities of animals is important for the purpose of monitoring their welfare vis a vis their behaviour with respect to their environment and conspecifics.