no code implementations • EMNLP (NLP-COVID19) 2020 • Shihan Wang, Marijn Schraagen, Erik Tjong Kim Sang, Mehdi Dastani
Public sentiment (the opinion, attitude or feeling that the public expresses) is a factor of interest for government, as it directly influences the implementation of policies.
no code implementations • 17 Jan 2025 • Maksim Gladyshev, Natasha Alechina, Mehdi Dastani, Dragan Doder, Brian Logan
Structural Equation Models (SEM) are the standard approach to representing causal dependencies between variables in causal models.
1 code implementation • 1 Oct 2024 • Francisco N. F. Q. Simoes, Mehdi Dastani, Thijs van Ommen
To effectively study complex causal systems, it is often useful to construct representations that simplify parts of the system by discarding irrelevant details while preserving key features.
1 code implementation • 15 Aug 2024 • Giovanni Varricchione, Natasha Alechina, Mehdi Dastani, Brian Logan
We prove that learning using such "maximally permissive" reward machines results in higher rewards than learning using RMs based on a single plan.
no code implementations • 18 May 2024 • Samira Shirzadeh-hajimahmood, I. S. W. B. Prasteya, Mehdi Dastani, Frank Dignum
Automated testing of computer games is a challenging problem, especially when lengthy scenarios have to be tested.
no code implementations • 2 Feb 2024 • Francisco N. F. Q. Simoes, Mehdi Dastani, Thijs van Ommen
These measures, named causal entropy and causal information gain, aim to address limitations in existing information theoretical approaches for machine learning tasks where causality plays a crucial role.
no code implementations • 25 Jan 2024 • Shuai Han, Mehdi Dastani, Shihan Wang
In this work, we propose an RL algorithm that can automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks.
no code implementations • 14 Sep 2023 • Francisco Nunes Ferreira Quialheiro Simoes, Mehdi Dastani, Thijs van Ommen
Specifically, we introduce causal versions of entropy and mutual information, termed causal entropy and causal information gain, which are designed to assess how much control a feature provides over the outcome variable.
no code implementations • 21 Jul 2023 • Jieting Luo, Thomas Studer, Mehdi Dastani
The increasing applications of AI systems require personalized explanations for their behaviors to various stakeholders since the stakeholders may have various knowledge and backgrounds.
no code implementations • 5 May 2023 • Yangyang Zhao, Zhenyu Wang, Mehdi Dastani, Shihan Wang
When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn.
no code implementations • 16 Mar 2022 • Changxi Zhu, Mehdi Dastani, Shihan Wang
In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance and achieve their objectives by communication.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+3
no code implementations • 5 Dec 2021 • Davide Dell'Anna, Natasha Alechina, Brian Logan, Maarten Löffler, Fabiano Dalpiaz, Mehdi Dastani
In this paper, we consider the problem of synthesising a norm from traces of agent behaviour, where each trace is labelled with whether the behaviour satisfies the system objective.
1 code implementation • 12 May 2021 • Saba Gholizadeh Ansari, I. S. W. B. Prasetya, Mehdi Dastani, Frank Dignum, Gabriele Keller
In this paper, we propose an automated player experience testing approach by suggesting a formal model of event-based emotions.
no code implementations • 22 Apr 2021 • Jurian Baas, Mehdi Dastani, Ad Feelders
The goal of entity matching in knowledge graphs is to identify entities that refer to the same real-world objects using some similarity metric.
no code implementations • 10 Mar 2021 • Chao Zhang, Shihan Wang, Henk Aarts, Mehdi Dastani
Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well.
1 code implementation • 12 Jun 2020 • Shihan Wang, Marijn Schraagen, Erik Tjong Kim Sang, Mehdi Dastani
Given the unprecedented nature of the COVID-19 crisis, having an up-to-date representation of public sentiment on governmental measures and announcements is crucial.
no code implementations • 17 Apr 2020 • Marc van Zee, Dragan Doder, Leendert van der Torre, Mehdi Dastani, Thomas Icard, Eric Pacuit
The first contribution is a logic for reasoning about intention, time and belief, in which assumptions of intentions are represented by preconditions of intended actions.
no code implementations • 23 Jan 2018 • Vahid Yazdanpanah, Mehdi Dastani
This paper builds on an existing notion of group responsibility and proposes two ways to define the degree of group responsibility: structural and functional degrees of responsibility.
no code implementations • 24 Aug 2016 • Natasha Alechina, Mehdi Dastani, Brian Logan
In this short note we address the issue of expressing norms (such as obligations and prohibitions) in temporal logic.