A Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analytics

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: A Comprehensive Workflow for Effective Imitation and Reinforcement Learning with Visual Analytics
Συγγραφείς: Metz, Yannick, Schlegel, Udo, Seebacher, Daniel, El-Assady, Mennatallah, Keim, Daniel A.
Στοιχεία εκδότη: The Eurographics Association, 2022.
Έτος έκδοσης: 2022
Θεματικοί όροι: Reinforcement learning, Visual analytics, Human centered computing, CCS Concepts: Human-centered computing --> Visual analytics, Computing methodologies --> Reinforcement learning, Computing methodologies
Περιγραφή: Multiple challenges hinder the application of reinforcement learning algorithms in experimental and real-world use cases even with recent successes in such areas. Such challenges occur at different stages of the development and deployment of such models. While reinforcement learning workflows share similarities with machine learning approaches, we argue that distinct challenges can be tackled and overcome using visual analytic concepts. Thus, we propose a comprehensive workflow for reinforcement learning and present an implementation of our workflow incorporating visual analytic concepts integrating tailored views and visualizations for different stages and tasks of the workflow.
Yannick Metz, Udo Schlegel, Daniel Seebacher, Mennatallah El-Assady, and Daniel Keim
Human-Model Collaboration and Personalization
Τύπος εγγράφου: Research
Conference object
Περιγραφή αρχείου: application/pdf
DOI: 10.2312/eurova.20221074
Σύνδεσμος πρόσβασης: http://nbn-resolving.de/urn:nbn:de:bsz:352-2-4e7iwot98daw9
Αριθμός Καταχώρησης: edsair.doi.dedup.....822e6c9e6023d7f4d6d59a355fa7c6e8
Βάση Δεδομένων: OpenAIRE