40 citations · 134 across the 31 of their papers we have counts for
32 papers
3vLTL: A Tool to Generate Automata for Three-valued LTL
Francesco Belardinelli, Angelo Ferrando, Vadim Malvone
Multi-valued logics have a long tradition in the literature on system verification, including run-time verification. However, comparatively fewer model-checking tools have been dev…
Strategic Abilities of Forgetful Agents in Stochastic Environments
Francesco Belardinelli, Wojciech Jamroga, Munyque Mittelmann +1
In this paper, we investigate the probabilistic variants of the strategy logics ATL and ATL* under imperfect information. Specifically, we present novel decidability and complexity…
Scalable Verification of Strategy Logic through Three-valued Abstraction
Francesco Belardinelli, Angelo Ferrando, Wojciech Jamroga +2
The model checking problem for multi-agent systems against Strategy Logic specifications is known to be non-elementary. On this logic several fragments have been defined to tackle…
Approximate Model-Based Shielding for Safe Reinforcement Learning
Alexander W. Goodall, Francesco Belardinelli
Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not ea…
Beyond Strict Competition: Approximate Convergence of Multi Agent Q-Learning Dynamics
Aamal Hussain, Francesco Belardinelli, Georgios Piliouras
The behaviour of multi-agent learning in competitive settings is often considered under the restrictive assumption of a zero-sum game. Only under this strict requirement is the beh…
Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
Aamal Hussain, Dan Leonte, Francesco Belardinelli +1
The behaviour of multi-agent learning in many player games has been shown to display complex dynamics outside of restrictive examples such as network zero-sum games. In addition, i…
Characterising Decision Theories with Mechanised Causal Graphs
Matt MacDermott, Tom Everitt, Francesco Belardinelli
How should my own decisions affect my beliefs about the outcomes I expect to achieve? If taking a certain action makes me view myself as a certain type of person, it might affect h…
Approximate Shielding of Atari Agents for Safe Exploration
Alexander W. Goodall, Francesco Belardinelli
Balancing exploration and conservatism in the constrained setting is an important problem if we are to use reinforcement learning for meaningful tasks in the real world. In this pa…
Asymptotic Convergence and Performance of Multi-Agent Q-Learning Dynamics
Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras
Achieving convergence of multiple learning agents in general -player games is imperative for the development of safe and reliable machine learning (ML) algorithms and their appl…
Argumentative Reward Learning: Reasoning About Human Preferences
Francis Rhys Ward, Francesco Belardinelli, Francesca Toni
We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from hum…
Program Semantics and a Verification Technique for Knowledge-Based Multi-Agent Systems
Francesco Belardinelli, Ioana Boureanu, Vadim Malvone +1
We give a relational and a weakest precondition semantics for "knowledge-based programs", i.e., programs that restrict observability of variables so as to richly express changes in…
A Sahlqvist-style Correspondence Theorem for Linear-time Temporal Logic
Rui Li, Francesco Belardinelli
The language of modal logic is capable of expressing first-order conditions on Kripke frames. The classic result by Henrik Sahlqvist identifies a significant class of modal formula…
Model Checking Strategic Abilities in Information-sharing Systems
Francesco Belardinelli, Ioana Boureanu, Catalin Dima +1
We introduce a subclass of concurrent game structures (CGS) with imperfect information in which agents are endowed with private data-sharing capabilities. Importantly, our CGSs are…
Bisimulations for Verifying Strategic Abilities with an Application to the ThreeBallot Voting Protocol
Francesco Belardinelli, Rodica Condurache, Catalin Dima +2
We propose a notion of alternating bisimulation for strategic abilities under imperfect information. The bisimulation preserves formulas of ATL for both the {\em objective} and…
Reasoning about Human-Friendly Strategies in Repeated Keyword Auctions
Francesco Belardinelli, Wojtek Jamroga, Vadim Malvone +3
In online advertising, search engines sell ad placements for keywords continuously through auctions. This problem can be seen as an infinitely repeated game since the auction is ex…
Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding
Chloe He, Borja G. Leon, Francesco Belardinelli
The growing trend of fledgling reinforcement learning systems making their way into real-world applications has been accompanied by growing concerns for their safety and robustness…
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications
Borja G. León, Murray Shanahan, Francesco Belardinelli
We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinfor…
An Abstraction-based Method to Check Multi-Agent Deep Reinforcement-Learning Behaviors
Pierre El Mqirmi, Francesco Belardinelli, Borja G. León
Multi-agent reinforcement learning (RL) often struggles to ensure the safe behaviours of the learning agents, and therefore it is generally not adapted to safety-critical applicati…
Aggregating Bipolar Opinions (With Appendix)
Stefan Lauren, Francesco Belardinelli, Francesca Toni
We introduce a novel method to aggregate Bipolar Argumentation (BA) Frameworks expressing opinions by different parties in debates. We use Bipolar Assumption-based Argumentation (A…
A Hennessy-Milner Theorem for ATL with Imperfect Information
Francesco Belardinelli, Catalin Dima, Vadim Malvone +1
We show that a history-based variant of alternating bisimulation with imperfect information allows it to be related to a variant of Alternating-time Temporal Logic (ATL) with imper…
Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning
Borja G. León, Murray Shanahan, Francesco Belardinelli
This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, gener…
Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning
Borja G. León, Francesco Belardinelli
The combination of Formal Methods with Reinforcement Learning (RL) has recently attracted interest as a way for single-agent RL to learn multiple-task specifications. In this paper…
Formal Verification of Debates in Argumentation Theory
Ria Jha, Francesco Belardinelli, Francesca Toni
Humans engage in informal debates on a daily basis. By expressing their opinions and ideas in an argumentative fashion, they are able to gain a deeper understanding of a given prob…
Social Choice Methods for Database Aggregation
Francesco Belardinelli, Umberto Grandi
Knowledge can be represented compactly in multiple ways, from a set of propositional formulas, to a Kripke model, to a database. In this paper we study the aggregation of informati…