Explaining Deep Q-Learning Experience Replay with SHapley Additive exPlanations

Reinforcement Learning (RL) has shown promise in optimizing complex control and decision-making processes but Deep Reinforcement Learning (DRL) lacks interpretability, limiting its adoption in regulated sectors like manufacturing, finance, and healthcare. Difficulties arise from DRL’s opaque decisio...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Robert S. Sullivan, Luca Longo
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2023-10-01
Serier:	Machine Learning and Knowledge Extraction
Fag:	deep reinforcement learning experience replay SHapley Additive exPlanations eXplainable artificial intelligence
Online adgang:	https://www.mdpi.com/2504-4990/5/4/72
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!