no code implementations • 11 Feb 2024 • Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt
In addition, we show how our definition relates to past concepts, including actual causality, and the notion of instrumental goals, which is a core idea in the literature on safe AI agents.
1 code implementation • 1 Feb 2024 • Alexander W. Goodall, Francesco Belardinelli
Shielding is a popular technique for achieving safe reinforcement learning (RL).
no code implementations • 19 Dec 2023 • Aamal Hussain, Francesco Belardinelli
Motivated by this we study the Q-Learning dynamics, a popular model of exploration and exploitation in multi-agent learning, in competitive network games.
no code implementations • NeurIPS 2023 • Francis Rhys Ward, Francesco Belardinelli, Francesca Toni, Tom Everitt
There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games.
no code implementations • 16 Nov 2023 • Francesco Belardinelli, Angelo Ferrando, Vadim Malvone
Multi-valued logics have a long tradition in the literature on system verification, including run-time verification.
1 code implementation • 27 Jul 2023 • Alexander W. Goodall, Francesco Belardinelli
Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains.
no code implementations • 26 Jul 2023 • Aamal Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras
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.
no code implementations • 20 Jul 2023 • Matt MacDermott, Tom Everitt, Francesco Belardinelli
How should my own decisions affect my beliefs about the outcomes I expect to achieve?
no code implementations • 21 Apr 2023 • 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.
no code implementations • 23 Jan 2023 • Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras
Achieving convergence of multiple learning agents in general $N$-player games is imperative for the development of safe and reliable machine learning (ML) algorithms and their application to autonomous systems.
no code implementations • 28 Sep 2022 • 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 human feedback.
no code implementations • 13 Jun 2022 • Rui Li, Francesco Belardinelli
The main result of this paper is to prove the correspondence of LTL Sahlqvist formulas to frame conditions that are definable in first-order language.
no code implementations • 19 Apr 2022 • Francesco Belardinelli, Ioana Boureanu, Catalin Dima, Vadim Malvone
To underline, the fragment of ATL for which we show the model-checking problem to be decidable over A-cast is a large and significant one; it expresses coalitions over agents in any subset of the set A.
no code implementations • 24 Jan 2022 • Francesco Belardinelli, Wojtek Jamroga, Vadim Malvone, Munyque Mittelmann, Aniello Murano, Laurent Perrussel
In online advertising, search engines sell ad placements for keywords continuously through auctions.
no code implementations • 21 Dec 2021 • Peter 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.
1 code implementation • ICLR 2022 • 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 reinforcement learning (DRL).
no code implementations • 4 Feb 2021 • Stefan Lauren, Francesco Belardinelli, Francesca Toni
We introduce a novel method to aggregate Bipolar Argumentation (BA) Frameworks expressing opinions by different parties in debates.
no code implementations • 2 Feb 2021 • 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 applications.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 12 Jun 2020 • 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, generalisation of formally specified instructions.
1 code implementation • 14 Feb 2020 • 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.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 12 Dec 2019 • Ria Jha, Francesco Belardinelli, Francesca Toni
Such transition systems can model debates and represent their evolution over time using a finite set of states.
no code implementations • 22 Jul 2019 • 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.
no code implementations • 23 Feb 2018 • Francesco Belardinelli, Umberto Grandi
Knowledge can be represented compactly in a multitude ways, from a set of propositional formulas, to a Kripke model, to a database.
Databases
no code implementations • 27 Jul 2017 • Francesco Belardinelli, Hans van Ditmarsch, Wiebe van der Hoek
In this paper we introduce {\em global and local announcement logic} (GLAL), a dynamic epistemic logic with two distinct announcement operators -- $[\phi]^+_A$ and $[\phi]^-_A$ indexed to a subset $A$ of the set $Ag$ of all agents -- for global and local announcements respectively.
no code implementations • 27 Jul 2017 • Francesco Belardinelli, Umberto Grandi, Andreas Herzig, Dominique Longin, Emiliano Lorini, Arianna Novaro, Laurent Perrussel
We introduce Concurrent Game Structures with Shared Propositional Control (CGS-SPC) and show that they ac- count for several classes of repeated games, including iterated boolean games, influence games, and aggregation games.
no code implementations • 3 Apr 2014 • Francesco Belardinelli
In this paper we introduce Epistemic Strategy Logic (ESL), an extension of Strategy Logic with modal operators for individual knowledge.
no code implementations • 23 Jan 2014 • Francesco Belardinelli, Alessio Lomuscio
We investigate a class of first-order temporal-epistemic logics for reasoning about multi-agent systems.