12 citations · 44 across the 41 of their papers we have counts for
42 papers
Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning
Davide Domini, Gianluca Aguzzi, Ivana Dusparic +2
Federated Learning often suffers under non-independently and identically distributed data, where a single global model may fail to represent the diversity of client distributions.…
Geographically-aware Transformer-based Traffic Forecasting for Urban Motorway Digital Twins
Krešimir Kušić, Vinny Cahill, Ivana Dusparic
The operational effectiveness of digital-twin technology in motorway traffic management depends on the availability of a continuous flow of high-resolution real-time traffic data.…
Adapting the Behavior of Reinforcement Learning Agents to Changing Action Spaces and Reward Functions
Raul de la Rosa, Ivana Dusparic, Nicolas Cardozo
Reinforcement Learning (RL) agents often struggle in real-world applications where environmental conditions are non-stationary, particularly when reward functions shift or the avai…
Continual Reinforcement Learning for Cyber-Physical Systems: Lessons Learned and Open Challenges
Kim N. Nolle, Ivana Dusparic, Rhodri Cusack +1
Continual learning (CL) is a branch of machine learning that aims to enable agents to adapt and generalise previously learned abilities so that these can be reapplied to new tasks…
Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
Alberto Castagna
Reinforcement Learning (RL) enables an intelligent agent to optimise its performance in a task by continuously taking action from an observed state and receiving a feedback from th…
Applying Neural Monte Carlo Tree Search to Unsignalized Multi-intersection Scheduling for Autonomous Vehicles
Yucheng Shi, Wenlong Wang, Xiaowen Tao +2
Dynamic scheduling of access to shared resources by autonomous systems is a challenging problem, characterized as being NP-hard. The complexity of this task leads to a combinatoria…
Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
Wenlong Wang, Ivana Dusparic, Yucheng Shi +2
Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires…
Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems
Juan C. Rosero, Ivana Dusparic, Nicolás Cardozo
Reinforcement Learning (RL) is used extensively in Autonomous Systems (AS) as it enables learning at runtime without the need for a model of the environment or predefined actions.…
Semifactual Explanations for Reinforcement Learning
Jasmina Gajcin, Jovan Jeromela, Ivana Dusparic
Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent th…
ACTER: Diverse and Actionable Counterfactual Sequences for Explaining and Diagnosing RL Policies
Jasmina Gajcin, Ivana Dusparic
Understanding how failure occurs and how it can be prevented in reinforcement learning (RL) is necessary to enable debugging, maintain user trust, and develop personalized policies…
Learning Recovery Strategies for Dynamic Self-healing in Reactive Systems
Mateo Sanabria, Ivana Dusparic, Nicolas Cardozo
Self-healing systems depend on following a set of predefined instructions to recover from a known failure state. Failure states are generally detected based on domain specific spec…
Iterative Reward Shaping using Human Feedback for Correcting Reward Misspecification
Jasmina Gajcin, James McCarthy, Rahul Nair +3
A well-defined reward function is crucial for successful training of an reinforcement learning (RL) agent. However, defining a suitable reward function is a notoriously challenging…
Density-Aware Reinforcement Learning to Optimise Energy Efficiency in UAV-Assisted Networks
Babatunji Omoniwa, Boris Galkin, Ivana Dusparic
Unmanned aerial vehicles (UAVs) serving as aerial base stations can be deployed to provide wireless connectivity to mobile users, such as vehicles. However, the density of vehicles…
Reservation of Virtualized Resources with Optimistic Online Learning
Jean-Baptiste Monteil, George Iosifidis, Ivana Dusparic
The virtualization of wireless networks enables new services to access network resources made available by the Network Operator (NO) through a Network Slicing market. The different…
Prevalence of Code Smells in Reinforcement Learning Projects
Nicolás Cardozo, Ivana Dusparic, Christian Cabrera
Reinforcement Learning (RL) is being increasingly used to learn and adapt application behavior in many domains, including large-scale and safety critical systems, as for example, a…
RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning
Jasmina Gajcin, Ivana Dusparic
While reinforcement learning (RL) algorithms have been successfully applied to numerous tasks, their reliance on neural networks makes their behavior difficult to understand and tr…
Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
Alberto Castagna, Ivana Dusparic
Transfer learning in Reinforcement Learning (RL) has been widely studied to overcome training issues of Deep-RL, i.e., exploration cost, data availability and convergence time, by…
Causal Counterfactuals for Improving the Robustness of Reinforcement Learning
Tom He, Jasmina Gajcin, Ivana Dusparic
Reinforcement learning (RL) is used in various robotic applications. RL enables agents to learn tasks autonomously by interacting with the environment. The more critical the tasks…
Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning
Jernej Hribar, Luke Hackett, Ivana Dusparic
In this paper, we build on advances introduced by the Deep Q-Networks (DQN) approach to extend the multi-objective tabular Reinforcement Learning (RL) algorithm W-learning to large…
Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities
Jasmina Gajcin, Ivana Dusparic
While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-…
Communication-Enabled Deep Reinforcement Learning to Optimise Energy-Efficiency in UAV-Assisted Networks
Babatunji Omoniwa, Boris Galkin, Ivana Dusparic
Unmanned aerial vehicles (UAVs) are increasingly deployed to provide wireless connectivity to static and mobile ground users in situations of increased network demand or points of…
Boolean Decision Rules for Reinforcement Learning Policy Summarisation
James McCarthy, Rahul Nair, Elizabeth Daly +2
Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context. Understanding the decisions and…
Guidelines for Artifacts to Support Industry-Relevant Research on Self-Adaptation
Danny Weyns, Ilias Gerostathopoulos, Barbora Buhnova +16
Artifacts support evaluating new research results and help comparing them with the state of the art in a field of interest. Over the past years, several artifacts have been introdu…
FedSA: Accelerating Intrusion Detection in Collaborative Environments with Federated Simulated Annealing
Helio N. Cunha Neto, Ivana Dusparic, Diogo M. F. Mattos +1
Fast identification of new network attack patterns is crucial for improving network security. Nevertheless, identifying an ongoing attack in a heterogeneous network is a non-trivia…