Agent's actions as a classification criteria for the state space in a learning from rewards system

DOI10.1080/09528130701538190zbMath1160.68508OpenAlexW2061133144MaRDI QIDQ3543672

Francisco Martinez-Gil

Publication date: 4 December 2008

Published in: Journal of Experimental & Theoretical Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/09528130701538190

zbMATH Keywords

intelligent agentsclassification by actionsstate space's clustering

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Other programming paradigms (object-oriented, sequential, concurrent, automatic, etc.) (68N19)

Cites Work

• Unnamed Item
• Stochastic dynamic programming with factored representations
• Adaptive aggregation methods for infinite horizon dynamic programming

This page was built for publication: Agent's actions as a classification criteria for the state space in a learning from rewards system