Explainable goal-driven agents and robots-a comprehensive review

F Sado, CK Loo, WS Liew, M Kerzel… - ACM Computing …, 2023 - dl.acm.org
Recent applications of autonomous agents and robots have brought attention to crucial trust-
related challenges associated with the current generation of artificial intelligence (AI) …

Explanatory artificial intelligence (YAI): human-centered explanations of explainable AI and complex data

F Sovrano, F Vitali - Data Mining and Knowledge Discovery, 2022 - Springer
In this paper we introduce a new class of software tools engaged in delivering successful
explanations of complex processes on top of basic Explainable AI (XAI) software systems …

Attention Loss Adjusted Prioritized Experience Replay

Z Chen, H Li, R Wang - arXiv preprint arXiv:2309.06684, 2023 - arxiv.org
Prioritized Experience Replay (PER) is a technical means of deep reinforcement learning by
selecting experience samples with more knowledge quantity to improve the training rate of …

Generating user-centred explanations via illocutionary question answering: From philosophy to interfaces

F Sovrano, F Vitali - ACM Transactions on Interactive Intelligent Systems, 2022 - dl.acm.org
We propose a new method for generating explanations with Artificial Intelligence (AI) and a
tool to test its expressive power within a user interface. In order to bridge the gap between …

Autonomous Driving via Knowledge-Enhanced Safe Reinforcement Learning

C Wang, L Wang, Z Lu, S Zhou, C Wu… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Recently, the autonomous driving technology is at a critical phase evolving from typical,
closed scenarios to largescale, open driving scenarios, which is challenged by the diversity …

How to improve the explanatory power of an intelligent textbook: a case study in legal writing

F Sovrano, K Ashley, PL Brusilovsky, F Vitali - International Journal of …, 2024 - Springer
Explanatory processes are at the core of scientific investigation, legal reasoning, and
education. However, effectively explaining complex or large amounts of information, such as …

Explaining Deep Q-Learning Experience Replay with SHapley Additive exPlanations

RS Sullivan, L Longo - Machine Learning and Knowledge Extraction, 2023 - mdpi.com
Reinforcement Learning (RL) has shown promise in optimizing complex control and
decision-making processes but Deep Reinforcement Learning (DRL) lacks interpretability …

Crossover in mutation oriented norm evolution

B Lv, X Wang, R Zhang - Complex & Intelligent Systems, 2024 - Springer
Norms are a coordination mechanism. They control agents' behavior in a multiagent system
(MAS) and need to evolve to cope with changing environments. Mutation oriented norm …

How to explain: from theory to practice

F Sovrano - 2023 - amsdottorato.unibo.it
Today we live in an age where the internet and artificial intelligence allow us to search for
information through impressive amounts of data, opening up revolutionary new ways to …