Optimization of State Clustering and Safety Verification in Deep Reinforcement Learning Using KMeans++ and Probabilistic Model Checking

Optimization of State Clustering and Safety Verification in Deep Reinforcement Learning Using KMeans++ and Probabilistic Model Checking

Ensuring the safety of Deep Reinforcement Learning (DRL) systems remains a significant challenge, particularly in real-time applications such as autonomous driving and robotics, where incorrect decisions can lead to catastrophic failures. This study proposes a novel safety verification framework tha...

Full description

Bibliographic Details
Main Authors: Ryeonggu Kwon, Gihwon Kwon
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Safety verification
deep reinforcement learning
state clustering
discrete-time Markov chain
Online Access:https://ieeexplore.ieee.org/document/10879317/

Internet

https://ieeexplore.ieee.org/document/10879317/

Similar Items