default search action
Francesco Belardinelli
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
- [j13]Charles Dickie, Stefan Lauren, Francesco Belardinelli, Antonio Rago, Francesca Toni:
Aggregating bipolar opinions through bipolar assumption-based argumentation. Auton. Agents Multi Agent Syst. 39(1): 4 (2025) - 2024
- [c80]Aamal Abbas Hussain, Francesco Belardinelli:
Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos. AAAI 2024: 17435-17443 - [c79]Francesco Belardinelli, Wojtek Jamroga, Munyque Mittelmann, Aniello Murano:
Verification of Stochastic Multi-Agent Systems with Forgetful Strategies. AAMAS 2024: 160-169 - [c78]Aamal Abbas Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras:
On the Stability of Learning in Network Games with Many Players. AAMAS 2024: 861-870 - [c77]Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt:
The Reasons that Agents Act: Intention and Instrumental Goals. AAMAS 2024: 1901-1909 - [c76]Alexander W. Goodall, Francesco Belardinelli:
Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments. AAMAS 2024: 2291-2293 - [i31]Alexander W. Goodall, Francesco Belardinelli:
Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments. CoRR abs/2402.00816 (2024) - [i30]Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt:
The Reasons that Agents Act: Intention and Instrumental Goals. CoRR abs/2402.07221 (2024) - [i29]Aamal Abbas Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras:
On the Stability of Learning in Network Games with Many Players. CoRR abs/2403.15848 (2024) - 2023
- [j12]Francesco Belardinelli, Angelo Ferrando, Vadim Malvone:
An abstraction-refinement framework for verifying strategic properties in multi-agent systems with imperfect information. Artif. Intell. 316: 103847 (2023) - [c75]Francesco Belardinelli, Ioana Boureanu, Vadim Malvone, Fortunat Rajaona:
Automatically Verifying Expressive Epistemic Properties of Programs. AAAI 2023: 6245-6252 - [c74]Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras:
Asymptotic Convergence and Performance of Multi-Agent Q-learning Dynamics. AAMAS 2023: 1578-1586 - [c73]Francis Rhys Ward, Francesca Toni, Francesco Belardinelli:
Defining Deception in Structural Causal Games. AAMAS 2023: 2902-2904 - [c72]Alexander W. Goodall, Francesco Belardinelli:
Approximate Model-Based Shielding for Safe Reinforcement Learning. ECAI 2023: 883-890 - [c71]Solofomampionona Fortunat Rajaona, Ioana Boureanu, Vadim Malvone, Francesco Belardinelli:
Program Semantics and Verification Technique for AI-Centred Programs. FM 2023: 473-491 - [c70]Aamal Abbas Hussain, Francesco Belardinelli, Dario Paccagnan:
The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics. ICML 2023: 14178-14202 - [c69]Francesco Belardinelli, Angelo Ferrando, Wojciech Jamroga, Vadim Malvone, Aniello Murano:
Scalable Verification of Strategy Logic through Three-Valued Abstraction. IJCAI 2023: 46-54 - [c68]Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras:
Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics. IJCAI 2023: 135-143 - [c67]Francesco Belardinelli, Wojciech Jamroga, Munyque Mittelmann, Aniello Murano:
Strategic Abilities of Forgetful Agents in Stochastic Environments. KR 2023: 726-731 - [c66]Francis Ward, Francesca Toni, Francesco Belardinelli, Tom Everitt:
Honesty Is the Best Policy: Defining and Mitigating AI Deception. NeurIPS 2023 - [c65]Hisham Unniyankal, Francesco Belardinelli, Angelo Ferrando, Vadim Malvone:
RMLGym: a Formal Reward Machine Framework for Reinforcement Learning. WOA 2023: 1-16 - [c64]Francesco Belardinelli, Angelo Ferrando, Vadim Malvone:
3vLTL: A Tool to Generate Automata for Three-valued LTL. FMAS@iFM 2023: 180-187 - [i28]Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras:
Asymptotic Convergence and Performance of Multi-Agent Q-Learning Dynamics. CoRR abs/2301.09619 (2023) - [i27]Alexander W. Goodall, Francesco Belardinelli:
Approximate Shielding of Atari Agents for Safe Exploration. CoRR abs/2304.11104 (2023) - [i26]Matt MacDermott, Tom Everitt, Francesco Belardinelli:
Characterising Decision Theories with Mechanised Causal Graphs. CoRR abs/2307.10987 (2023) - [i25]Aamal Abbas Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras:
Stability of Multi-Agent Learning: Convergence in Network Games with Many Players. CoRR abs/2307.13922 (2023) - [i24]Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras:
Beyond Strict Competition: Approximate Convergence of Multi Agent Q-Learning Dynamics. CoRR abs/2307.13928 (2023) - [i23]Alexander W. Goodall, Francesco Belardinelli:
Approximate Model-Based Shielding for Safe Reinforcement Learning. CoRR abs/2308.00707 (2023) - [i22]Francesco Belardinelli, Angelo Ferrando, Wojciech Jamroga, Vadim Malvone, Aniello Murano:
Scalable Verification of Strategy Logic through Three-valued Abstraction. CoRR abs/2310.17219 (2023) - [i21]Francesco Belardinelli, Wojciech Jamroga, Munyque Mittelmann, Aniello Murano:
Strategic Abilities of Forgetful Agents in Stochastic Environments. CoRR abs/2310.17240 (2023) - [i20]Francis Rhys Ward, Francesco Belardinelli, Francesca Toni, Tom Everitt:
Honesty Is the Best Policy: Defining and Mitigating AI Deception. CoRR abs/2312.01350 (2023) - [i19]Aamal Abbas Hussain, Francesco Belardinelli:
Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos. CoRR abs/2312.11943 (2023) - 2022
- [j11]Francesco Belardinelli, Alessio Lomuscio, Vadim Malvone, Emily Yu:
Approximating Perfect Recall when Model Checking Strategic Abilities: Theory and Applications. J. Artif. Intell. Res. 73: 897-932 (2022) - [c63]Chloe He, Borja G. León, Francesco Belardinelli:
Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding. SafeAI@AAAI 2022 - [c62]Francesco Belardinelli, Wojtek Jamroga, Vadim Malvone, Munyque Mittelmann, Aniello Murano, Laurent Perrussel:
Reasoning about Human-Friendly Strategies in Repeated Keyword Auctions. AAMAS 2022: 62-71 - [c61]Francis Rhys Ward, Francesca Toni, Francesco Belardinelli:
On Agent Incentives to Manipulate Human Feedback in Multi-Agent Reward Learning Scenarios. AAMAS 2022: 1759-1761 - [c60]Francesco Belardinelli, Borja G. León, Vadim Malvone:
Enabling Markovian Representations under Imperfect Information. ICAART (2) 2022: 450-457 - [c59]Francis Rhys Ward, Francesca Toni, Francesco Belardinelli:
A Causal Perspective on AI Deception in Games. ICLP Workshops 2022 - [c58]Borja G. León, Murray Shanahan, Francesco Belardinelli:
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications. ICLR 2022 - [c57]Francis Rhys Ward, Francesco Belardinelli, Francesca Toni:
A causal perspective on AI deception in games. AISafety@IJCAI 2022 - [i18]Francesco Belardinelli, Wojtek Jamroga, Vadim Malvone, Munyque Mittelmann, Aniello Murano, Laurent Perrussel:
Reasoning about Human-Friendly Strategies in Repeated Keyword Auctions. CoRR abs/2201.09616 (2022) - [i17]Francesco Belardinelli, Rodica Condurache, Catalin Dima, Wojciech Jamroga, Michal Knapik:
Bisimulations for Verifying Strategic Abilities with an Application to the ThreeBallot Voting Protocol. CoRR abs/2203.13692 (2022) - [i16]Francesco Belardinelli, Ioana Boureanu, Catalin Dima, Vadim Malvone:
Model Checking Strategic Abilities in Information-sharing Systems. CoRR abs/2204.08896 (2022) - [i15]Rui Li, Francesco Belardinelli:
A Sahlqvist-style Correspondence Theorem for Linear-time Temporal Logic. CoRR abs/2206.05973 (2022) - [i14]Francesco Belardinelli, Ioana Boureanu, Vadim Malvone, Solofomampionona Fortunat Rajaona:
Program Semantics and a Verification Technique for Knowledge-Based Multi-Agent Systems. CoRR abs/2206.13841 (2022) - [i13]Francis Rhys Ward, Francesco Belardinelli, Francesca Toni:
Argumentative Reward Learning: Reasoning About Human Preferences. CoRR abs/2209.14010 (2022) - 2021
- [j10]Francesco Belardinelli, Stéphane Demri:
Strategic reasoning with a bounded number of resources: The quest for tractability. Artif. Intell. 300: 103557 (2021) - [j9]Francesco Belardinelli, Rodica Condurache, Catalin Dima, Wojciech Jamroga, Michal Knapik:
Bisimulations for verifying strategic abilities with an application to the ThreeBallot voting protocol. Inf. Comput. 276: 104552 (2021) - [c56]Pierre El Mqirmi, Francesco Belardinelli, Borja G. León:
An Abstraction-based Method to Check Multi-Agent Deep Reinforcement-Learning Behaviors. AAMAS 2021: 474-482 - [c55]Stefan Lauren, Francesco Belardinelli, Francesca Toni:
Aggregating Bipolar Opinions. AAMAS 2021: 746-754 - [c54]Shibei Zhu, Francesco Belardinelli, Borja Gonzalez León:
Evolutionary reinforcement learning for sparse rewards. GECCO Companion 2021: 1508-1512 - [c53]Francesco Belardinelli, Sophia Knight, Alessio Lomuscio, Bastien Maubert, Aniello Murano, Sasha Rubin:
Reasoning About Agents That May Know Other Agents' Strategies. IJCAI 2021: 1787-1793 - [i12]Pierre El Mqirmi, Francesco Belardinelli, Borja G. León:
An Abstraction-based Method to Verify Multi-Agent Deep Reinforcement-Learning Behaviours. CoRR abs/2102.01434 (2021) - [i11]Stefan Lauren, Francesco Belardinelli, Francesca Toni:
Aggregating Bipolar Opinions (With Appendix). CoRR abs/2102.02881 (2021) - [i10]Borja G. León, Murray Shanahan, Francesco Belardinelli:
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications. CoRR abs/2110.09461 (2021) - [i9]Chloe He, Borja G. León, Francesco Belardinelli:
Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding. CoRR abs/2112.11490 (2021) - 2020
- [j8]Francesco Belardinelli, Alessio Lomuscio, Aniello Murano, Sasha Rubin:
Verification of multi-agent systems with public actions against strategy logic. Artif. Intell. 285: 103302 (2020) - [c52]Francesco Belardinelli, Alessio Lomuscio, Emily Yu:
Model Checking Temporal Epistemic Logic under Bounded Recall. AAAI 2020: 7071-7078 - [c51]Francesco Belardinelli, Vadim Malvone:
Verifying Strategic Abilities in Multi-Agent Systems via First-Order Entailment. ECAI 2020: 27-34 - [c50]Borja G. León, Francesco Belardinelli:
Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning. ECAI 2020: 139-146 - [c49]Francesco Belardinelli, Stéphane Demri:
Reasoning with a Bounded Number of Resources in ATL+. ECAI 2020: 624-631 - [c48]Francesco Belardinelli, Vadim Malvone:
A Three-valued Approach to Strategic Abilities under Imperfect Information. KR 2020: 89-98 - [c47]Francesco Belardinelli, Catalin Dima, Vadim Malvone, Ferucio Laurentiu Tiplea:
A Hennessy-Milner Theorem for ATL with Imperfect Information. LICS 2020: 181-194 - [c46]Ria Jha, Francesco Belardinelli, Francesca Toni:
Formal verification of debates in argumentation theory. SAC 2020: 940-947 - [i8]Borja G. León, Francesco Belardinelli:
Extended Markov Games to Learn Multiple Tasks in Multi-Agent Reinforcement Learning. CoRR abs/2002.06000 (2020) - [i7]Borja G. León, Murray Shanahan, Francesco Belardinelli:
Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning. CoRR abs/2006.08767 (2020) - [i6]Francesco Belardinelli, Catalin Dima, Vadim Malvone, Ferucio Laurentiu Tiplea:
A Hennessy-Milner Theorem for ATL with Imperfect Information. CoRR abs/2006.15000 (2020)
2010 – 2019
- 2019
- [c45]Francesco Belardinelli, Alessio Lomuscio, Vadim Malvone:
An Abstraction-Based Method for Verifying Strategic Properties in Multi-Agent Systems with Imperfect Information. AAAI 2019: 6030-6037 - [c44]Francesco Belardinelli, Stéphane Demri:
Resource-bounded ATL: the Quest for Tractable Fragments. AAMAS 2019: 206-214 - [c43]Francesco Belardinelli, Umberto Grandi:
A Social Choice Theoretic Perspective on Database Aggregation. AAMAS 2019: 1817-1819 - [c42]Francesco Belardinelli, Ioana Boureanu, Catalin Dima, Vadim Malvone:
Verifying Strategic Abilities in Multi-agent Systems with Private Data-Sharing. AAMAS 2019: 1820-1822 - [c41]Francesco Belardinelli, Wojciech Jamroga, Damian Kurpiewski, Vadim Malvone, Aniello Murano:
Strategy Logic with Simple Goals: Tractable Reasoning about Strategies. IJCAI 2019: 88-94 - [c40]Francesco Belardinelli, Vadim Malvone:
Decidable Verification of Agent-Based Data-Aware Systems. PRIMA 2019: 52-68 - [c39]Francesco Belardinelli, Alessio Lomuscio, Aniello Murano, Sasha Rubin:
Imperfect Information in Alternating-Time Temporal Logic on Finite Traces. PRIMA 2019: 469-477 - [c38]Francesco Belardinelli, Umberto Grandi:
Social Choice Methods for Database Aggregation. TARK 2019: 50-67 - [i5]Francesco Belardinelli, Catalin Dima, Ioana Boureanu, Vadim Malvone:
Model Checking ATL* on vCGS. CoRR abs/1903.04350 (2019) - [i4]Ria Jha, Francesco Belardinelli, Francesca Toni:
Formal Verification of Debates in Argumentation Theory. CoRR abs/1912.05828 (2019) - 2018
- [j7]Francesco Belardinelli, Wiebe van der Hoek, Louwe B. Kuijer:
Second-order propositional modal logic: Expressiveness and completeness results. Artif. Intell. 263: 3-45 (2018) - [c37]Francesco Belardinelli, Alessio Lomuscio, Aniello Murano, Sasha Rubin:
Decidable Verification of Multi-agent Systems with Bounded Private Actions. AAMAS 2018: 1865-1867 - [c36]Francesco Belardinelli, Alessio Lomuscio, Aniello Murano, Sasha Rubin:
Alternating-time Temporal Logic on Finite Traces. IJCAI 2018: 77-83 - [c35]Francesco Belardinelli, Catalin Dima, Aniello Murano:
Bisimulations for Logics of Strategies: A Study in Expressiveness and Verification. KR 2018: 425-434 - [c34]Francesco Belardinelli, Alessio Lomuscio, Vadim Malvone:
Approximating Perfect Recall When Model Checking Strategic Abilities. KR 2018: 435-444 - [e1]Francesco Belardinelli, Estefania Argente:
Multi-Agent Systems and Agreement Technologies - 15th European Conference, EUMAS 2017, and 5th International Conference, AT 2017, Évry, France, December 14-15, 2017, Revised Selected Papers. Lecture Notes in Computer Science 10767, Springer 2018, ISBN 978-3-030-01712-5 [contents] - [i3]Francesco Belardinelli, Umberto Grandi:
Database Aggregation. CoRR abs/1802.08586 (2018) - 2017
- [c33]Francesco Belardinelli, Alessio Lomuscio:
Agent-based Abstractions for Verifying Alternating-time Temporal Logic with Imperfect Information. AAMAS 2017: 1259-1267 - [c32]Francesco Belardinelli, Alessio Lomuscio, Aniello Murano, Sasha Rubin:
Verification of Multi-agent Systems with Imperfect Information and Public Actions. AAMAS 2017: 1268-1276 - [c31]Francesco Belardinelli, Rodica Condurache, Catalin Dima, Wojciech Jamroga, Andrew V. Jones:
Bisimulations for Verifying Strategic Abilities with an Application to ThreeBallot. AAMAS 2017: 1286-1295 - [c30]Francesco Belardinelli, Alessio Lomuscio, Aniello Murano, Sasha Rubin:
Verification of Broadcasting Multi-Agent Systems against an Epistemic Strategy Logic. IJCAI 2017: 91-97 - [c29]Francesco Belardinelli, Panagiotis Kouvaros, Alessio Lomuscio:
Parameterised Verification of Data-aware Multi-Agent Systems. IJCAI 2017: 98-104 - [c28]Francesco Belardinelli, Andreas Herzig:
Dynamic Logic for Data-aware Systems: Decidability Results. IJCAI 2017: 821-827 - [c27]Francesco Belardinelli, Hans van Ditmarsch, Wiebe van der Hoek:
A Logic for Global and Local Announcements. TARK 2017: 28-42 - [c26]Francesco Belardinelli, Umberto Grandi, Andreas Herzig, Dominique Longin, Emiliano Lorini, Arianna Novaro, Laurent Perrussel:
Relaxing Exclusive Control in Boolean Games. TARK 2017: 43-56 - 2016
- [c25]Francesco Belardinelli, Wiebe van der Hoek:
A Semantical Analysis of Second-Order Propositional Modal Logic. AAAI 2016: 886-892 - [c24]Francesco Belardinelli, Hans van Ditmarsch, Wiebe van der Hoek:
Second-order Propositional Announcement Logic. AAMAS 2016: 635-643 - [c23]Francesco Belardinelli, Alessio Lomuscio, Jakub Michaliszyn:
Agent-Based Refinement for Predicate Abstraction of Multi-Agent Systems. ECAI 2016: 286-294 - [c22]Francesco Belardinelli, Alessio Lomuscio:
Abstraction-Based Verification of Infinite-State Reactive Modules. ECAI 2016: 725-733 - [c21]Francesco Belardinelli, Andreas Herzig:
On Logics of Strategic Ability Based on Propositional Control. IJCAI 2016: 95-101 - [c20]Francesco Belardinelli, Alessio Lomuscio:
A Three-Value Abstraction Technique for the Verification of Epistemic Properties in Multi-agent Systems. JELIA 2016: 112-126 - 2015
- [c19]Francesco Belardinelli, Davide Grossi:
On the Formal Verification of Diffusion Phenomena in Open Dynamic Agent Networks. AAMAS 2015: 237-245 - [c18]Francesco Belardinelli, Davide Grossi, Alessio Lomuscio:
Finite Abstractions for the Verification of Epistemic Properties in Open Multi-Agent Systems. IJCAI 2015: 854-860 - [c17]Francesco Belardinelli, Davide Grossi, Nicolas Maudet:
Formal Analysis of Dialogues on Infinite Argumentation Frameworks. IJCAI 2015: 861-867 - [c16]Francesco Belardinelli, Wiebe van der Hoek:
Epistemic Quantified Boolean Logic: Expressiveness and Completeness Results. IJCAI 2015: 2748-2754 - 2014
- [j6]Francesco Belardinelli, Alessio Lomuscio, Fabio Patrizi:
Verification of Agent-Based Artifact Systems. J. Artif. Intell. Res. 51: 333-376 (2014) - [c15]Francesco Belardinelli:
Verification of non-uniform and unbounded artifact-centric systems: decidability through abstraction. AAMAS 2014: 717-724 - [c14]Francesco Belardinelli:
Model Checking Auctions as Artifact Systems: Decidability via Finite Abstraction. ECAI 2014: 81-86 - [c13]Francesco Belardinelli:
Satisfiability of Alternating-Time Temporal Epistemic Logic Through Tableaux. KR 2014 - [c12]Francesco Belardinelli:
Reasoning about Knowledge and Strategies: Epistemic Strategy Logic. SR 2014: 27-33 - [i2]Francesco Belardinelli, Alessio Lomuscio:
Interactions between Knowledge and Time in a First-Order Logic for Multi-Agent Systems: Completeness Results. CoRR abs/1401.5849 (2014) - 2013
- [c11]Francesco Belardinelli, Alessio Lomuscio:
Decidability of Model Checking Non-Uniform Artifact-Centric Quantified Interpreted Systems. IJCAI 2013: 725-731 - [i1]Francesco Belardinelli, Alessio Lomuscio, Fabio Patrizi:
Verification of Agent-Based Artifact Systems. CoRR abs/1301.2678 (2013) - 2012
- [j5]Francesco Belardinelli, Alessio Lomuscio:
Interactions between Knowledge and Time in a First-Order Logic for Multi-Agent Systems: Completeness Results. J. Artif. Intell. Res. 45: 1-45 (2012) - [c10]Francesco Belardinelli, Alessio Lomuscio, Fabio Patrizi:
Verification of GSM-Based Artifact-Centric Systems through Finite Abstraction. ICSOC 2012: 17-31 - [c9]Francesco Belardinelli, Alessio Lomuscio, Fabio Patrizi:
An Abstraction Technique for the Verification of Artifact-Centric Systems. KR 2012 - [c8]Francesco Belardinelli, Pavel Gonzalez, Alessio Lomuscio:
Automated Verification of Quantum Protocols using MCMAS. QAPL 2012: 48-62 - 2011
- [j4]Francesco Belardinelli, Alessio Lomuscio:
First-Order Linear-time Epistemic Logic with Group Knowledge: An Axiomatisation of the Monodic Fragment. Fundam. Informaticae 106(2-4): 175-190 (2011) - [j3]Francesco Belardinelli, Andrew V. Jones, Alessio Lomuscio:
Model Checking Temporal-Epistemic Logic Using Alternating Tree Automata. Fundam. Informaticae 112(1): 19-37 (2011) - [c7]Francesco Belardinelli, Alessio Lomuscio, Fabio Patrizi:
Verification of Deployed Artifact Systems via Data Abstraction. ICSOC 2011: 142-156 - [c6]Francesco Belardinelli, Alessio Lomuscio, Fabio Patrizi:
A Computationally-Grounded Semantics for Artifact-Centric Systems and Abstraction Results. IJCAI 2011: 738-743 - 2010
- [c5]Francesco Belardinelli, Alessio Lomuscio:
Interactions between Time and Knowledge in a First-order Logic for Multi-Agent Systems. KR