Fig 5 - A Fast Technique for Smart Home Management: ADP with Temporal Difference Learning

Illustration of the modified Markov decision process, which separates the state variables into post decision states and pre-decision states.

Go to figure page

Reference

A Fast Technique for Smart Home Management: ADP with Temporal Difference Learning - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/Illustration-of-the-modified-Markov-decision-process-which-separates-the-state-variables_fig8_310582166 [accessed 16 Aug, 2022]

Caption

Fig. 5. Illustration of the modified Markov decision process, which separates the state variables into post decision states and pre-decision states.

Embed code

<a href="https://www.researchgate.net/figure/Illustration-of-the-modified-Markov-decision-process-which-separates-the-state-variables_fig8_310582166"><img src="https://www.researchgate.net/profile/Chanaka-Keerthisinghe/publication/310582166/figure/fig8/AS:668590311223325@1536415760856/Illustration-of-the-modified-Markov-decision-process-which-separates-the-state-variables.png" alt="Illustration of the modified Markov decision process, which separates the state variables into post decision states and pre-decision states."/></a>