Supporting Architectural Decision Making on Training Strategies in Reinforcement Learning ArchitecturesResearch Paper
In the dynamic landscape of artificial intelligence and machine learning, Reinforcement Learning (RL) has emerged as a powerful paradigm for training intelligent agents in sequential decision-making. As RL architectures progress in complexity, the need for informed decision-making regarding training strategies and related consequences on the software architecture becomes increasingly intricate. This work addresses this challenge by presenting the outcomes of a qualitative, in-depth study focused on best practices and patterns within training strategies for RL architectures, as articulated by practitioners. Leveraging a model-based qualitative research method, we introduce a formal architecture decision model to bridge the gap between scientific insights and practical implementation. We aim to enhance the understanding of practitioners’ approaches in RL architecture. The paper analyzes 33 knowledge sources to discern established industrial practices, patterns, relationships, and decision drivers. Based on this knowledge, we introduce a formal Architectural Design Decision (ADD) model, encapsulating 6 decisions, 29 decision options, and 19 decision drivers, providing robust decision-making support for this critical facet of RL-based software architectures.
Fri 7 JunDisplayed time zone: Chennai, Kolkata, Mumbai, New Delhi change
14:00 - 15:30 | Session 6A: Architecture Design & Rationale 1New and Emerging Ideas / Research Papers Session Chair: Ingo Weber, TU Munich and Fraunhofer Gesellschaft | ||
14:00 25mResearch paper | Informed and Assessable Observability Design Decisions in Cloud-native Microservice ApplicationsResearch Paper Research Papers A: Maria C Borges Technische Universität Berlin, A: Joshua Bauer Technische Universität Berlin, A: Sebastian Werner TU Berlin, Germany, A: Michael Gebauer TU Berlin, Germany, A: Stefan Tai Technische Universität Berlin Pre-print | ||
14:25 25mResearch paper | Can LLMs Generate Architectural Design Decisions? - An Exploratory Empirical studyResearch Paper Research Papers A: Rudra Dhar SERC, IIIT Hyderabad, India, A: Karthik Vaidhyanathan IIIT Hyderabad, A: Vasudeva Varma International Institute of Information Technology Hyderabad Pre-print | ||
14:50 25mResearch paper | Supporting Architectural Decision Making on Training Strategies in Reinforcement Learning ArchitecturesResearch Paper Research Papers A: Evangelos Ntentos University of Vienna, A: Stephen John Warnett University of Vienna, A: Uwe Zdun University of Vienna | ||
15:15 20mResearch paper | Towards Connecting Bugs and Architecture in Software Systems: A PerspectiveNEMI New and Emerging Ideas |