Filetype
Recent methods for imitation learning directly learn a Q-function using an implicit reward formulation rather than an explicit reward function.However, these methods generally require implicit reward regularization to improve stability and often mistreat absorbing states.Previous works show that a squared norm regularization on the implicit reward function is effective, but do not provide a theore
Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a ro
Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or non-differentiable policies. Furthermore, these approaches are particularly relevant where exploration at the action level could cause actuator damage or other safety issues. H
Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting
Learning robot motions from demonstration requires models able to specify vector fields for the full robot pose when the task is defined in operational space. Recent advances in reactive motion generation have shown that learning adaptive, reactive, smooth, and stable vector fields is possible. However, these approaches define vector fields on a flat Euclidean manifold, while representing vector f
Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all. Similarly, if the agent receives also rewards that create suboptimal modes of the objective function, it will likely prematurely stop exploring. More
Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When deploying RL to the real world, several concerns regarding the use of a 'black-box' policy might be raised. In order to make the learned policies more transparent, we
Mango production plays a vital role in rural livelihoods in Mozambique, yet post-harvest losses remain high, ranging from 25% to over 50%, due to inadequate preservation methods. Improved solar drying technologies offer a sustainable solution by extending shelf life and enhancing product quality. However, their adoption among smallholder mango farmers remains limited. This study investigates the k
Poly(butylene adipate-co-terephthalate) (PBAT) is an important commercial biodegradable flexible copolyester, which is dependent on the fossil-based terephthalates for production. In the present work, two series of PBAT-mimicking copolyesters are synthesized using lignin-sourced aromatic monomers, i.e., methyl 4-(2-hydroxyethoxy) vanillate and methyl 4-(2-hydroxyethoxy) benzoate, aliphatic dimethy
Semantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. Although previous studies provide insight into the cognitive underpinnings of semantic representations, they have suffered from small sample sizes and a lack of linguistic and cultural diversity. In this Registered Report, we measured the size and the variability of the seman
Over the past fifteen years, Rwanda has made significant progress in formalizing mining rights and the production processes of 3Ts minerals in its artisanal and small-scale mining (ASM) sector. However, labour relations remain largely unregulated. This study analyses ASM activities through the production process observations, document reviews, and interviews with key informants involved in the sec
Darknet constitutes a part of the internet with a reputation for allowing deviance and criminality. In short, it is often understood as a place where anything goes. Current research on Darknet tends to focus on illicit cryptomarkets, however in this ongoing doctoral research project, I explore how user posts and behaviors are informally and formally controlled and shaped on Darknet forums. Moreove
Global clothing consumption is increasing, with many garments having unnecessarily short lifetimes due to low quality materials and manufacturing, often linked to price pressures. Current European Union strategies focus on improving technical durability, product maintenance, and waste collection, but fail to address the role of the consumer for durable garments. A better understanding of drivers a
Regular, vigorous physical activity can have a significant impact on cardiac function, leading to cardiac morphological alterations that may be challenging to distinguish from pathological changes. Therefore, new screening methods are needed to accurately differentiate between adaptive changes and pathological alterations in athletes. Vortex formation time (VFT) is an emerging method that shows po
Objectives: The aim of the present study was to assess if vortex formation time (VFT) as a measurement of left ventricular (LV) diastolic function is affected by food intake and related to age and sex. Methods: Healthy participants were divided into two age groups: younger (median age: 25 years) and older (median age: 68 years). Transthoracic echocardiography (TTE) examinations were performed duri
