Now showing1 - 3 of 3
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: with files ,
    Scilab-RL: a software framework for efficient reinforcement learning and cognitive modeling research
    (Elsevier, 2025-01-31) ; ;
    One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current RL algorithms exist, but there is a lack of a modular suite of tools combining different robotic simulators and platforms, data visualization, hyperparameter optimization, and baseline experiments. To address this problem, we present Scilab-RL, a software framework for efficient research in cognitive modeling and reinforcement learning for robotic agents. The framework focuses on goal-conditioned reinforcement learning using Stable Baselines 3, CleanRL and the Gymnasium interface. It enables native possibilities for experiment visualizations and hyperparameter optimization. We describe how these features enable researchers to conduct experiments with minimal time effort, thus maximizing research output.
    Publicationtype: Journal Article
      29  23
  • Some of the metrics are blocked by your 
    Item type:Publication,
    MUSEN : an open-source framework for GPU-accelerated DEM simulations
    (Elsevier, 2020-11-12) ;
    The conceptual design, implementation aspects and main features of an open-source DEM simulation framework MUSEN have been described. MUSEN has been developed for efficient calculations that can be performed on personal computers equipped with general-purpose graphics processing units (GPUs). A very intuitive graphical user interface significantly simplifies usage of the system and reduces learning time. It makes this framework an ideal software tool for educational purposes and for solution of classical problems of solids process engineering. Users without significant experience can easily specify initial scenes, perform simulations and analyse results. In the same time, the modular-based structure of the system allows its extension with new components, calculation algorithms or contact models.
    Publicationtype: Journal Article
      222
  • Some of the metrics are blocked by your 
    Item type:Publication, Access status: with files ,
    Dyssol — an open-source flowsheet simulation framework for particulate materials
    Dyssol is a modelling framework for the dynamic flowsheet simulation of processes designed for handling of particulate materials. Main distinctive features of this software are the comprehensive description of multidimensionally distributed particulate materials, the application of transformation matrices and the use of sequential-modular simulation approach. This cross-platform system can be easily extended with new models, applied for calculation of large datasets and coupled to the external programme packages.
    Publicationtype: Journal Article
    Scopus© Citations 14  316  338