Kevin Mets
YOU?
Author Swipe
Temporal distillation: compressing a policy in space and time Open
Deploying deep reinforcement learning on resource-constrained devices remains a significant challenge due to the energy-intensive nature of the sequential decision-making process. Model compression can reduce the spatial (e.g. storage, mem…
Advances in Continual Graph Learning for Anti‐Money Laundering Systems: A Comprehensive Review Open
Financial institutions are required by regulation to report suspicious financial transactions related to money laundering. Therefore, they need to constantly monitor vast amounts of incoming and outgoing transactions. Given the involvement…
Designing a Classifier for Active Fire Detection From Multispectral Satellite Imagery Using Neural Architecture Search Open
Wildfires are becoming increasingly devastating, and detecting them early is essential to containing them. Deep learning-based wildfire detection systems have increased in complexity dramatically in recent years, and in order to manage thi…
Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer Learning Open
Recently, a novel paradigm has been proposed for reinforcement learning-based NAS agents, that revolves around the incremental improvement of a given architecture. We assess the abilities of such reinforcement learning agents to transfer b…
Scalable reinforcement learning-based neural architecture search Open
We assess the feasibility of a reusable neural architecture search agent aimed at amortizing the initial time-investment in building a good search strategy. We do this through the use of Reinforcement Learning, where an agent learns to ite…
A hybrid predictive modeling approach for catalyzed polymerization reactors Open
Polymerization reactions are characterized by complex, nonlinear behaviors that pose significant challenges for conventional modeling techniques. Accurate and reliable models are crucial for advancing material science and enabling technolo…
Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search Open
This paper showcases the use of a reinforcement learning-based Neural Architecture Search (NAS) agent to design a small neural network to perform active fire detection on multispectral satellite imagery. Specifically, we aim to design a ne…
Scalable Reinforcement Learning-based Neural Architecture Search Open
In this publication, we assess the ability of a novel Reinforcement Learning-based solution to the problem of Neural Architecture Search, where a Reinforcement Learning (RL) agent learns to search for good architectures, rather than to ret…
Policy Compression for Intelligent Continuous Control on Low-Power Edge Devices Open
Interest in deploying deep reinforcement learning (DRL) models on low-power edge devices, such as Autonomous Mobile Robots (AMRs) and Internet of Things (IoT) devices, has seen a significant rise due to the potential of performing real-tim…
Dataset Condensation with Latent Quantile Matching Open
Dataset condensation (DC) methods aim to learn a smaller synthesized dataset with informative data records to accelerate the training of machine learning models. Current distribution matching (DM) based DC methods learn a synthesized datas…
Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition Open
Continual learning (CL) is the research field that aims to build machine\nlearning models that can accumulate knowledge continuously over different tasks\nwithout retraining from scratch. Previous studies have shown that pre-training\ngrap…
Unsupervised Domain Adaptation for Human Pose Action Recognition Open
Personalized human action recognition is important to give accurate feedback about motion patterns, but there is likely no labeled data available to update the model in a supervised way.Unsupervised domain adaptation can solve this problem…
Physical Ergonomics Anticipation with Human Motion Prediction Open
Good physical ergonomics is a crucial aspect of performing repetitive tasks sustainably for a long period.We developed a VR training environment that improves the ergonomics and experience of the user during a task.Through human motion pre…
Scalability of Message Encoding Techniques for Continuous Communication Learned with Multi-Agent Reinforcement Learning Open
Many multi-agent systems require inter-agent communication to properly achieve their goal. By learning the communication protocol alongside the action protocol using multi-agent reinforcement learning techniques, the agents gain the flexib…
An In-Depth Analysis of Discretization Methods for Communication Learning using Backpropagation with Multi-Agent Reinforcement Learning Open
Communication is crucial in multi-agent reinforcement learning when agents are not able to observe the full state of the environment. The most common approach to allow learned communication between agents is the use of a differentiable com…
Structured Exploration Through Instruction Enhancement for Object Navigation Open
Finding an object of a specific class in an unseen environment remains an unsolved navigation problem. Hence, we propose a hierarchical learning-based method for object navigation. The top-level is capable of high-level planning, and build…
Safety Aware Autonomous Path Planning Using Model Predictive Reinforcement Learning for Inland Waterways Open
In recent years, interest in autonomous shipping in urban waterways has\nincreased significantly due to the trend of keeping cars and trucks out of city\ncenters. Classical approaches such as Frenet frame based planning and potential\nfiel…
An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning Open
Communication is crucial in multi-agent reinforcement learning when agents are not able to observe the full state of the environment. The most common approach to allow learned communication between agents is the use of a differentiable com…
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges Open
Reinforcement learning (RL) allows an agent to solve sequential decision-making problems by interacting with an environment in a trial-and-error fashion. When these environments are very complex, pure random exploration of possible solutio…
Deep Set Conditioned Latent Representations for Action Recognition Open
In recent years multi-label, multi-class video action recognition has gained\nsignificant popularity. While reasoning over temporally connected atomic\nactions is mundane for intelligent species, standard artificial neural networks\n(ANN) …
Learning to Communicate with Reinforcement Learning for an Adaptive Traffic Control System Open
Recent work in multi-agent reinforcement learning has investigated inter agent communication which is learned simultaneously with the action policy in order to improve the team reward. In this paper, we investigate independent Q-learning (…
ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs Open
IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-…
HTMRL: Biologically Plausible Reinforcement Learning with Hierarchical Temporal Memory Open
Building Reinforcement Learning (RL) algorithms which are able to adapt to continuously evolving tasks is an open research challenge. One technology that is known to inherently handle such non-stationary input patterns well is Hierarchical…