Related papers: A structured approach to VO reconfigurations throu…

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Service Oriented Architecture (SOA) is an architectural paradigm that describes how organizations, people and systems provide and use services to achieve their goals and enhance productivity. Moreover, with the evolution of SOA, the focus…

Performing tasks on the web presents fundamental challenges to large language models (LLMs), including combinatorially large open-world tasks and variations across web interfaces. Simply specifying a large prompt to handle all possible…

Despite many works on collaborative networked organizations (CNOs), CSCW, groupware, workflow systems and social networks, computer support for virtual teams is still insufficient, especially support for agility, i.e. the capability of…

We propose the concept of adaptable processes as a way of overcoming the limitations that process calculi have for describing patterns of dynamic process evolution. Such patterns rely on direct ways of controlling the behavior and location…

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Enhancing the diversity of policies is beneficial for robustness, exploration, and transfer in reinforcement learning (RL). In this paper, we aim to seek diverse policies in an under-explored setting, namely RL tasks with structured action…

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation, but their reliance on expert demonstrations limits their ability to learn from failures and perform self-corrections. Reinforcement…

Visual-Language-Action (VLA) models have demonstrated strong cross-scenario generalization capabilities in various robotic tasks through large-scale pre-training and task-specific fine-tuning. However, their training paradigm mainly relies…

System-Theoretic Process Analysis (STPA) is a recommended method for analysing complex systems, capable of identifying thousands of safety requirements often missed by traditional techniques such as Failure Mode and Effects Analysis (FMEA)…

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected…

Allocating resources to virtualized network functions and services to meet service level agreements is a challenging task for NFV management and orchestration systems. This becomes even more challenging when agile development methodologies,…

Software engineers frequently face the challenge of developing systems whose requirements are likely to change in order to adapt to organizational reconfigurations or other external pressures. Evolving requirements present difficulties,…

In this project we demonstrate the effectiveness of the transformer encoder as a viable architecture for policies in variable action environments. Using it, we train an agent using Proximal Policy Optimisation (PPO) on multiple maps against…

The VIPAFLEET project consists in developing models and algorithms for man- aging a fleet of Individual Public Autonomous Vehicles (VIPA). Hereby, we consider a fleet of cars distributed at specified stations in an industrial area to supply…

While current autonomous navigation systems allow robots to successfully drive themselves from one point to another in specific environments, they typically require extensive manual parameter re-tuning by human robotics experts in order to…

Adaptability is a significant property which enables software systems to continuously provide the required functionality and achieve optimal performance. The recognised importance of adaptability makes its evaluation an essential task.…

Fog computing is a promising computing paradigm in which IoT data can be processed near the edge to support time-sensitive applications. However, the availability of the resources in the computation device is not stable since they may not…

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…