Logo des Repositoriums

Auflistung nach Schlagwort "Multi-task learning"

1 - 4 von 4
  • Zeitschriftenartikel
    Accounting for Task-Difficulty in Active Multi-Task Robot Control Learning
    (KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Fabisch, Alexander; Metzen, Jan Hendrik; Krell, Mario Michael; Kirchner, Frank
    Contextual policy search is a reinforcement learning approach for multi-task learning in the context of robot control learning. It can be used to learn versatilely applicable skills that generalize over a range of tasks specified by a context vector. In this work, we combine contextual policy search with ideas from active learning for selecting the task in which the next trial will be performed. Moreover, we use active training set selection for reducing detrimental effects of exploration in the sampling policy. A core challenge in this approach is that the distribution of the obtained rewards may not be directly comparable between different tasks. We propose the novel approach PUBSVE for estimating a reward baseline and investigate empirically on benchmark problems and simulated robotic tasks to which extent this method can remedy the issue of non-comparable reward.
  • Zeitschriftenartikel
    Habilitation Abstract: Towards Explainable Fact Checking
    (KI - Künstliche Intelligenz: Vol. 36, No. 0, 2022) Augenstein, Isabelle
    With the substantial rise in the amount of mis- and disinformation online, fact checking has become an important task to automate. This article is a summary of a habilitation (doctor scientiarum) thesis submitted to the University of Copenhagen, which was sucessfully defended in December 2021 (Augenstein in Towards Explainable Fact Checking. Dr. Scient. thesis, University of Copenhagen, Faculty of Science, 2021). The dissertation addresses several fundamental research gaps within automatic fact checking. The contributions are organised along three verticles: (1) the fact-checking subtask they address; (2) methods which only require small amounts of manually labelled data; (3) methods for explainable fact checking, addressing the problem of opaqueness in the decision-making of black-box fact checking models.
  • Zeitschriftenartikel
    Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning
    (KI - Künstliche Intelligenz: Vol. 35, No. 1, 2021) Nguyen, Sao Mai; Duminy, Nicolas; Manoury, Alexandre; Duhaut, Dominique; Buche, Cedric
    Multi-task learning by robots poses the challenge of the domain knowledge: complexity of tasks, complexity of the actions required, relationship between tasks for transfer learning. We demonstrate that this domain knowledge can be learned to address the challenges in life-long learning. Specifically, the hierarchy between tasks of various complexities is key to infer a curriculum from simple to composite tasks. We propose a framework for robots to learn sequences of actions of unbounded complexity in order to achieve multiple control tasks of various complexity. Our hierarchical reinforcement learning framework, named SGIM-SAHT, offers a new direction of research, and tries to unify partial implementations on robot arms and mobile robots. We outline our contributions to enable robots to map multiple control tasks to sequences of actions: representations of task dependencies, an intrinsically motivated exploration to learn task hierarchies, and active imitation learning. While learning the hierarchy of tasks, it infers its curriculum by deciding which tasks to explore first, how to transfer knowledge, and when, how and whom to imitate.
  • Zeitschriftenartikel
    Towards Learning of Generic Skills for Robotic Manipulation
    (KI - Künstliche Intelligenz: Vol. 28, No. 1, 2014) Metzen, Jan Hendrik; Fabisch, Alexander; Senger, Lisa; Gea Fernández, José; Kirchner, Elsa Andrea
    Learning versatile, reusable skills is one of the key prerequisites for autonomous robots. Imitation and reinforcement learning are among the most prominent approaches for learning basic robotic skills. However, the learned skills are often very specific and cannot be reused in different but related tasks. In the project 'Behaviors for Mobile Manipulation', we develop hierarchical and transfer learning methods which allow a robot to learn a repertoire of versatile skills that can be reused in different situations. The development of new methods is closely integrated with the analysis of complex human behavior.