This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
memento-value-function-approximation [2025/09/14 07:44] 66.249.68.35 old revision restored (2025/08/29 20:14) |
memento-value-function-approximation [2025/09/17 07:29] (current) 20.171.207.36 old revision restored (2025/08/31 03:58) |
||
---|---|---|---|
Line 52: | Line 52: | ||
* Optimise le MSE (mean squarred error) entre les cibles du QNetwork et du QLearning | * Optimise le MSE (mean squarred error) entre les cibles du QNetwork et du QLearning | ||
* Utilise une variante de la descente de gradient stochastique | * Utilise une variante de la descente de gradient stochastique | ||
- | + | | |