LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 43

Search options

  1. Thesis ; Online: Reinforcement Learning and Optimal Experimental Design for Modeling and Control of Fish Schooling Hydrodynamics

    Weber, Pascal Philippe Martin

    2023  

    Abstract: This doctoral thesis investigates the modeling and control of fish hydrodynamics. The study consists of two main components: computational modeling of flow fields and sensory cues, and understanding the optimality principles driving fish behavior. The ... ...

    Abstract This doctoral thesis investigates the modeling and control of fish hydrodynamics. The study consists of two main components: computational modeling of flow fields and sensory cues, and understanding the optimality principles driving fish behavior. The thesis emphasizes the incorporation of hydrodynamic interactions to accurately represent the fish’s environment. The research utilizes reinforcement learning, Bayesian inference, and high-performance computing to analyze natural behavior and flow fields. The insights gained from this study have potential applications in autonomous robot swimmers and may inspire new experiments in biology. Efficient and scalable implemen- tations of computation fluid dynamics, reinforcement learning, and Bayesian inference algorithms are developed to address the computational challenge and pave the way for future advancements in the field.
    Keywords info:eu-repo/classification/ddc/000 ; info:eu-repo/classification/ddc/004 ; info:eu-repo/classification/ddc/510 ; info:eu-repo/classification/ddc/530 ; info:eu-repo/classification/ddc/620 ; Generalities ; science ; Data processing ; computer science ; Mathematics ; Physics ; Engineering & allied operations
    Subject code 629
    Language English
    Publisher ETH Zurich
    Publishing country ch
    Document type Thesis ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  2. Book ; Online ; Thesis: Electrostatic anchoring of SNAP25 to the plasma membrane

    Weber, Pascal [Verfasser]

    2021  

    Author's details Pascal Weber
    Keywords Naturwissenschaften ; Science
    Subject code sg500
    Language English
    Publisher Universitäts- und Landesbibliothek Bonn
    Publishing place Bonn
    Document type Book ; Online ; Thesis
    Database Digital theses on the web

    More links

    Kategorien

  3. Article ; Online: Self-Sensing of a Magnetically Actuated Prism.

    Weber, Pascal M / Wallrabe, Ulrike / Wapler, Matthias C

    Sensors (Basel, Switzerland)

    2023  Volume 23, Issue 12

    Abstract: We demonstrate a method for self-sensing of a magnetically actuated prism that can be used, e.g., in a feedback-loop without the need of additional sensors. In order to use the impedance of the actuation coils as a measurement parameter, we first ... ...

    Abstract We demonstrate a method for self-sensing of a magnetically actuated prism that can be used, e.g., in a feedback-loop without the need of additional sensors. In order to use the impedance of the actuation coils as a measurement parameter, we first obtained the optimal measurement frequency that is well separated from the actuation frequencies and at the same time provides the best compromise between sensitivity to the position and robustness. We then developed a combined actuation and measurement driver, and correlated its output signal to the mechanical state of the prism using a defined calibration sequence. We demonstrate that we can reliably measure the state of each actuator and determine the tilt angle of the prism with an accuracy of ±0.1∘ in the polar angle over a range of ±4∘ and ±20 mrad in the azimuthal angle.
    Language English
    Publishing date 2023-06-10
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2052857-7
    ISSN 1424-8220 ; 1424-8220
    ISSN (online) 1424-8220
    ISSN 1424-8220
    DOI 10.3390/s23125493
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article: [No title information]

    Weber, Pascal

    Praxis

    2017  Volume 106, Issue 18, Page(s) 1011–1012

    Title translation Antidiabetika und Prostatakarzinomrisiko.
    Language German
    Publishing date 2017-12-14
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 209026-0
    ISSN 1661-8165 ; 1661-8157 ; 0369-8394
    ISSN (online) 1661-8165
    ISSN 1661-8157 ; 0369-8394
    DOI 10.1024/1661-8157/a002773
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article: [No title information]

    Weber, Pascal

    Praxis

    2017  Volume 106, Issue 10, Page(s) 545–546

    Title translation Unterschiede in der Effektivität und Komplikationsrate von transurethralen Operationstechniken bei symptomatischer Prostatahyperplasie.
    MeSH term(s) Follow-Up Studies ; Humans ; Male ; Postoperative Complications/etiology ; Prostatic Hyperplasia/surgery ; Randomized Controlled Trials as Topic ; Transurethral Resection of Prostate/methods ; Treatment Outcome
    Language German
    Publishing date 2017
    Publishing country Switzerland
    Document type Comparative Study ; Journal Article ; Meta-Analysis ; Review
    ZDB-ID 209026-0
    ISSN 1661-8165 ; 1661-8157 ; 0369-8394
    ISSN (online) 1661-8165
    ISSN 1661-8157 ; 0369-8394
    DOI 10.1024/1661-8157/a002668
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article: [No title information]

    Weber, Pascal

    Praxis

    2017  Volume 106, Issue 20, Page(s) 1127–1128

    Title translation Hypofraktionierte Radiotherapie für die Behandlung des lokal begrenzten Prostatakarzinoms mittleren Risikos.
    Language German
    Publishing date 2017
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 209026-0
    ISSN 1661-8165 ; 1661-8157 ; 0369-8394
    ISSN (online) 1661-8165
    ISSN 1661-8157 ; 0369-8394
    DOI 10.1024/1661-8157/a002801
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Book ; Online: Hubschrauber Außenlast Assistenz System (HALAS)

    Weber, Pascal

    Abschlussbericht ; Berichtszeitraum: 01.01.2010 bis 31.12.2013

    2014  

    Title variant HALAS
    Author's details Berichterstatter: Pascal Weber
    Language German ; English
    Size Online-Ressource (52 S., 5,282 MB), Ill., graph. Darst.
    Edition Rev: 1.00
    Publisher Techn. Informationsbibl. und Univ.-Bibl ; iMAR GmbH, Gesellschaft für inertiale Mess-, Automatisierungs- und Regelsysteme
    Publishing place Hannover ; St. Ingbert
    Document type Book ; Online
    Note Mit dt. u. engl. Zsfassung ; Förderkennzeichen BMWi 20H0907A. - Verbund-Nr. 01075621 ; Unterschiede zwischen dem gedruckten Dokument und der elektronischen Ressource können nicht ausgeschlossen werden
    Database Library catalogue of the German National Library of Science and Technology (TIB), Hannover

    More links

    Kategorien

  8. Book ; Online: Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning

    Waelchli, Daniel / Weber, Pascal / Koumoutsakos, Petros

    2023  

    Abstract: The discovery of individual objectives in collective behavior of complex dynamical systems such as fish schools and bacteria colonies is a long-standing challenge. Inverse reinforcement learning is a potent approach for addressing this challenge but its ... ...

    Abstract The discovery of individual objectives in collective behavior of complex dynamical systems such as fish schools and bacteria colonies is a long-standing challenge. Inverse reinforcement learning is a potent approach for addressing this challenge but its applicability to dynamical systems, involving continuous state-action spaces and multiple interacting agents, has been limited. In this study, we tackle this challenge by introducing an off-policy inverse multi-agent reinforcement learning algorithm (IMARL). Our approach combines the ReF-ER techniques with guided cost learning. By leveraging demonstrations, our algorithm automatically uncovers the reward function and learns an effective policy for the agents. Through extensive experimentation, we demonstrate that the proposed policy captures the behavior observed in the provided data, and achieves promising results across problem domains including single agent models in the OpenAI gym and multi-agent models of schooling behavior. The present study shows that the proposed IMARL algorithm is a significant step towards understanding collective dynamics from the perspective of its constituents, and showcases its value as a tool for studying complex physical systems exhibiting collective behaviour.
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Computer Science - Multiagent Systems
    Subject code 006
    Publishing date 2023-05-17
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  9. Book ; Online: Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning

    Weber, Pascal / Wälchli, Daniel / Zeqiri, Mustafa / Koumoutsakos, Petros

    2022  

    Abstract: We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). {ReF-ER} was shown to outperform state of the art algorithms for continuous control in problems ranging from the ... ...

    Abstract We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). {ReF-ER} was shown to outperform state of the art algorithms for continuous control in problems ranging from the OpenAI Gym to complex fluid flows. In MARL, the dependencies between the agents are included in the state-value estimator and the environment dynamics are modeled via the importance weights used by ReF-ER. In collaborative environments, we find the best performance when the value is estimated using individual rewards and we ignore the effects of other actions on the transition map. We benchmark the performance of ReF-ER MARL on the Stanford Intelligent Systems Laboratory (SISL) environments. We find that employing a single feed-forward neural network for the policy and the value function in ReF-ER MARL, outperforms state of the art algorithms that rely on complex neural network architectures.
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Mathematics - Optimization and Control ; Statistics - Machine Learning
    Subject code 006 ; 629
    Publishing date 2022-03-24
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  10. Book: Hubschrauber Außenlast Assistenz System (HALAS)

    Weber, Pascal

    Abschlussbericht ; Berichtszeitraum: 01.01.2010 bis 31.12.2013

    2014  

    Title variant HALAS
    Author's details Berichterstatter: Pascal Weber
    Language German ; English
    Size 50 Bl., Ill., graph. Darst.
    Edition Rev: 1.00
    Publisher iMAR GmbH, Gesellschaft für inertiale Mess-, Automatisierungs- und Regelsysteme
    Publishing place St. Ingbert
    Document type Book
    Note Mit dt. u. engl. Zsfassung ; Förderkennzeichen BMWi 20H0907A. - Verbund-Nr. 01075621 ; Unterschiede zwischen dem gedruckten Dokument und der elektronischen Ressource können nicht ausgeschlossen werden
    Database Library catalogue of the German National Library of Science and Technology (TIB), Hannover

    More links

    Kategorien

To top