The increasing applications of AI systems require personalized explanations for their behaviors to various stakeholders since the stakeholders may have various knowledge and backgrounds. In general, a conversation between explainers and explainees not only allows explainers to obtain the explainees' background, but also allows explainees to better understand the explanations. In this paper, we propose an approach for an explainer to communicate personalized explanations to an explainee through having consecutive conversations with the explainee. We prove that the conversation terminates due to the explainee's justification of the initial claim as long as there exists an explanation for the initial claim that the explainee understands and the explainer is aware of.

Most solutions to the inventory management problem assume a centralization of information that is incompatible with organisational constraints in real supply chain networks. The inventory management problem is a well-known planning problem in operations research, concerned with finding the optimal re-order policy for nodes in a supply chain. While many centralized solutions to the problem exist, they are not applicable to real-world supply chains made up of independent entities. The problem can however be naturally decomposed into sub-problems, each associated with an independent entity, turning it into a multi-agent system. Therefore, a decentralized data-driven solution to inventory management problems using multi-agent reinforcement learning is proposed where each entity is controlled by an agent. Three multi-agent variations of the proximal policy optimization algorithm are investigated through simulations of different supply chain networks and levels of uncertainty. The centralized training decentralized execution framework is deployed, which relies on offline centralization during simulation-based policy identification, but enables decentralization when the policies are deployed online to the real system. Results show that using multi-agent proximal policy optimization with a centralized critic leads to performance very close to that of a centralized data-driven solution and outperforms a distributed model-based solution in most cases while respecting the information constraints of the system.

Artificial Intelligence has been used to help human complete difficult tasks in complicated environments by providing optimized strategies for decision-making or replacing the manual labour. In environments including multiple agents, such as football, the most common methods to train agents are Imitation Learning and Multi-Agent Reinforcement Learning (MARL). However, the agents trained by Imitation Learning cannot outperform the expert demonstrator, which makes humans hardly get new insights from the learnt policy. Besides, MARL is prone to the credit assignment problem. In environments with sparse reward signal, this method can be inefficient. The objective of our research is to create a novel reward shaping method by embedding contextual information in reward function to solve the aforementioned challenges. We demonstrate this in the Google Research Football (GRF) environment. We quantify the contextual information extracted from game state observation and use this quantification together with original sparse reward to create the shaped reward. The experiment results in the GRF environment prove that our reward shaping method is a useful addition to state-of-the-art MARL algorithms for training agents in environments with sparse reward signal.

Process discovery studies ways to use event data generated by business processes and recorded by IT systems to construct models that describe the processes. Existing discovery algorithms are predominantly concerned with constructing process models that represent the control flow of the processes. Agent system mining argues that business processes often emerge from interactions of autonomous agents and uses event data to construct models of the agents and their interactions. This paper presents and evaluates Agent Miner, an algorithm for discovering models of agents and their interactions from event data composing the system that has executed the processes which generated the input data. The conducted evaluation using our open-source implementation of Agent Miner and publicly available industrial datasets confirms that our algorithm can provide insights into the process participants and their interaction patterns and often discovers models that describe the business processes more faithfully than process models discovered using conventional process discovery algorithms.

The use of Machine Learning (ML) has rapidly spread across several fields, having encountered many applications in Structural Dynamics and Vibroacoustic (SD\&V). The increasing capabilities of ML to unveil insights from data, driven by unprecedented data availability, algorithms advances and computational power, enhance decision making, uncertainty handling, patterns recognition and real-time assessments. Three main applications in SD\&V have taken advantage of these benefits. In Structural Health Monitoring, ML detection and prognosis lead to safe operation and optimized maintenance schedules. System identification and control design are leveraged by ML techniques in Active Noise Control and Active Vibration Control. Finally, the so-called ML-based surrogate models provide fast alternatives to costly simulations, enabling robust and optimized product design. Despite the many works in the area, they have not been reviewed and analyzed. Therefore, to keep track and understand this ongoing integration of fields, this paper presents a survey of ML applications in SD\&V analyses, shedding light on the current state of implementation and emerging opportunities. The main methodologies, advantages, limitations, and recommendations based on scientific knowledge were identified for each of the three applications. Moreover, the paper considers the role of Digital Twins and Physics Guided ML to overcome current challenges and power future research progress. As a result, the survey provides a broad overview of the present landscape of ML applied in SD\&V and guides the reader to an advanced understanding of progress and prospects in the field.

Devising a strategy to make a system mimic behaviors from another system is a problem that naturally arises in many areas of Computer Science. In this work, we interpret this problem in the context of intelligent agents, from the perspective of ltlf , a formalism commonly used in AI for expressing finite-trace properties. Our model consists of two separated dynamic domains, DA and DB, and an LTLf specification that formalizes the notion of mimicking by mapping properties on behaviors (traces) of DA into properties on behaviors of DB. The goal is to synthesize a strategy that step-by-step maps every behavior of DA into a behavior of DB so that the specification is met. We consider several forms of mapping specifications, ranging from simple ones to full LTLf , and for each, we study synthesis algorithms and computational properties.

Smart mobility becomes paramount for meeting net-zero targets. However, autonomous, self-driving and electric vehicles require more than ever before an efficient, resilient and trustworthy computational offloading backbone that expands throughout the edge-to-cloud continuum. Utilizing on-demand heterogeneous computational resources for smart mobility is challenging and often cost-ineffective. This paper introduces SMOTEC, a novel open-source testbed for adaptive smart mobility experimentation with edge computing. SMOTEC provides for the first time a modular end-to-end instrumentation for prototyping and optimizing placement of intelligence services on edge devices such as augmented reality and real-time traffic monitoring. SMOTEC supports a plug-and-play Docker container integration of the SUMO simulator for urban mobility, Raspberry Pi edge devices communicating via ZeroMQ and EPOS for an AI-based decentralized load balancing across edge-to-cloud. All components are orchestrated by the K3s lightweight Kubernetes. A proof-of-concept of self-optimized service placements for traffic monitoring from Munich demonstrates in practice the applicability and cost-effectiveness of SMOTEC.

When has an agent converged? Standard models of the reinforcement learning problem give rise to a straightforward definition of convergence: An agent converges when its behavior or performance in each environment state stops changing. However, as we shift the focus of our learning problem from the environment's state to the agent's state, the concept of an agent's convergence becomes significantly less clear. In this paper, we propose two complementary accounts of agent convergence in a framing of the reinforcement learning problem that centers around bounded agents. The first view says that a bounded agent has converged when the minimal number of states needed to describe the agent's future behavior cannot decrease. The second view says that a bounded agent has converged just when the agent's performance only changes if the agent's internal state changes. We establish basic properties of these two definitions, show that they accommodate typical views of convergence in standard settings, and prove several facts about their nature and relationship. We take these perspectives, definitions, and analysis to bring clarity to a central idea of the field.

Trajectory and control secrecy is an important issue in robotics security. This paper proposes a novel algorithm for the control input inference of a mobile agent without knowing its control objective. Specifically, the algorithm first estimates the target state by applying external perturbations. Then we identify the objective function based on the inverse optimal control, providing the well-posedness proof and the identifiability analysis. Next, we obtain the optimal estimate of the control horizon using binary search. Finally, the agent's control optimization problem is reconstructed and solved to predict its input. Simulation illustrates the efficiency and the performance of the algorithm.

To be successful, Vision-and-Language Navigation (VLN) agents must be able to ground instructions to actions based on their surroundings. In this work, we develop a methodology to study agent behavior on a skill-specific basis -- examining how well existing agents ground instructions about stopping, turning, and moving towards specified objects or rooms. Our approach is based on generating skill-specific interventions and measuring changes in agent predictions. We present a detailed case study analyzing the behavior of a recent agent and then compare multiple agents in terms of skill-specific competency scores. This analysis suggests that biases from training have lasting effects on agent behavior and that existing models are able to ground simple referring expressions. Our comparisons between models show that skill-specific scores correlate with improvements in overall VLN task performance.