Searched for: contributor%3A%22Kober%2C+Jens+%28mentor%29%22
(1 - 7 of 7)
document
Jacobs, Olav (author)
In this thesis, a control scheme for lifting parcels using two robot manipulators is presented. The robots do not have a rigid grasp on the object. Instead, they use friction to lift the parcels. First, a controller calculates the desired force to make sure the parcels do not slip. The required force, as well as a trajectory are then sent to a...
master thesis 2020
document
Kokkalis, Konstantinos (author)
Learning capabilities are a key requisite for an autonomous agent operating in dynamically changing and complex environments, where pre-programming is not anymore possible. Furthermore, it is essential to guarantee that the learning agent will act safely by considering its stability properties. In this thesis, novel conditions are proposed,...
master thesis 2018
document
Keulen, Bart (author)
An important problem in reinforcement learning is the exploration-exploitation dilemma. Especially for environments with sparse or misleading rewards it has proven difficult to construct a good exploration strategy. For discrete domains good exploration strategies have been devised, but are often nontrivial to implement on more complex domains...
master thesis 2018
document
Duan, Wuyang (author)
Representation learning is a central topic in the field of deep learning. It aims at extracting useful state representations directly from raw data. In deep learning, state representations are usually used for classification or inferences. For example, image embedding that provides similarity metrics can be used for face recognition. Recent...
master thesis 2017
document
Radojević, Jovana (author)
A lot of attention has recently been focused on possible benefits of the cooperation between machines and humans. Taking the best from machines and humans and joining them together can produce results which exceed each collaborating partner performing separately. A common belief is that the<br/>key for good cooperation is an excellent...
master thesis 2017
document
Ravi, Siddharth (author)
This project addresses a fundamental problem faced by many reinforcement learning agents. Commonly used reinforcement learning agents can be seen to have deteriorating performances at increasing frequencies, as they are unable to correctly learn the ordering of expected returns for actions that are applied. We call this the disappearing...
master thesis 2017
document
Rastogi, Divyam (author)
Reinforcement Learning (RL) is a general purpose framework for designing controllers for non-linear systems. It tries to learn a controller (policy) by trial and error. This makes it highly suitable for systems which are difficult to control using conventional control methodologies, such as walking robots. Traditionally, RL has only been...
master thesis 2017
Searched for: contributor%3A%22Kober%2C+Jens+%28mentor%29%22
(1 - 7 of 7)