QR-Code

Low Complexity and Scalable Architecture of Dual-Mode Training and Inference Hardware Accelerator for Deep Q-Network (DQN) Based Edge Computing

Reinforcement Learning (RL) has shown great potential in a wide range of applications, including robotics, autonomous vehicles, and communication systems. However, deploying RL on edge devices poses significant challenges due to limited computational resources and the complexity of real-time decisio...

Ausführliche Beschreibung

Gespeichert in:
Hauptverfasser: A. Sumarudin, Nana Sutisna, Infall Syafalni, Bambang Riyanto Trilaksono, Trio Adiono
Format: Artigo
Sprache:Inglês
Veröffentlicht: IEEE 2025-01-01
Schriftenreihe:IEEE Access
Schlagworte:
AI accelerator
deep Q-network (DQN)
edge computing
FPGA
reinforcement learning
Online-Zugang:https://ieeexplore.ieee.org/document/10971177/
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!

Ähnliche Einträge