SARSA - Historique des versions

Pitpitt : Remplacement de texte : « ↵ » par «  ==Sources== »

2024-01-28T17:18:46Z

Remplacement de texte : « ↵<small> » par «  ==Sources== »

← Version précédente		Version du 28 janvier 2024 à 13:18
Ligne 10 :		Ligne 10 :
	''' State–action–reward–state–action'''		''' State–action–reward–state–action'''

	~~<small>~~		==Sources==

	[https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action Source : Wikipedia Machine Learning ]		[https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action Source : Wikipedia Machine Learning ]

Pitpitt le 6 janvier 2022 à 04:35

2022-01-06T04:35:04Z

← Version précédente		Version du 6 janvier 2022 à 00:35
Ligne 17 :		Ligne 17 :


	[[Catégorie:~~publication~~]]		[[Catégorie:ENGLISH]]
	[[Catégorie:~~Wikipedia-IA‎~~]]
			[[Catégorie:GRAND LEXIQUE FRANÇAIS]]

Imeziani le 6 janvier 2022 à 00:47

2022-01-06T00:47:26Z

← Version précédente		Version du 5 janvier 2022 à 20:47
Ligne 1 :		Ligne 1 :
	~~==en construction==~~

	== Définition ==		== Définition ==
	~~XXXXXXXXX~~		En [[apprentissage par renforcement‎]], algorithme d'apprentissage dont l’acronyme anglais correspond à State-Action-Reward-State-Action, en français: État-Action-Récompense-État-Action. Il s'agit d'une légère variation du populaire algorithme [[apprentissage par fonction Q]].

	== Français ==		== Français ==
	''' ~~XXXXXXXXX~~ '''		'''SARSA'''

	== Anglais ==		== Anglais ==
			'''SARSA'''

	''' State–action–reward–state–action'''		''' State–action–reward–state–action'''

	~~'''SARSA'''~~

	State–action–reward–state–action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was proposed by Rummery and Niranjan in a technical note[1] with the name "Modified Connectionist Q-Learning" (MCQ-L). The alternative name SARSA, proposed by Rich Sutton, was only mentioned as a footnote.
	<small>		<small>

	[https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action Source : Wikipedia Machine Learning ]		[https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action Source : Wikipedia Machine Learning ]

			[https://fr.acervolima.com/apprentissage-par-renforcement-sarsa/ Source: Acervo Lima]


	[[Catégorie:~~vocabulary~~]]		[[Catégorie:publication]]
	[[Catégorie:Wikipedia-IA‎]]		[[Catégorie:Wikipedia-IA‎]]

Imeziani : Imeziani a déplacé la page State–action–reward–state–action vers SARSA

2022-01-06T00:37:57Z

Imeziani a déplacé la page State–action–reward–state–action vers SARSA

← Version précédente	Version du 5 janvier 2022 à 20:37
(Aucune différence)

Pitpitt le 3 janvier 2022 à 21:07

2022-01-03T21:07:56Z

← Version précédente		Version du 3 janvier 2022 à 17:07
Ligne 9 :		Ligne 9 :
	== Anglais ==		== Anglais ==
	''' State–action–reward–state–action'''		''' State–action–reward–state–action'''

			'''SARSA'''

	State–action–reward–state–action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was proposed by Rummery and Niranjan in a technical note[1] with the name "Modified Connectionist Q-Learning" (MCQ-L). The alternative name SARSA, proposed by Rich Sutton, was only mentioned as a footnote.		State–action–reward–state–action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was proposed by Rummery and Niranjan in a technical note[1] with the name "Modified Connectionist Q-Learning" (MCQ-L). The alternative name SARSA, proposed by Rich Sutton, was only mentioned as a footnote.

Pitpitt : Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == ''' State–action–reward–state–action''' State–action–reward... »

2020-12-17T16:50:27Z

Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == ''' State–action–reward–state–action''' State–action–reward... »

Nouvelle page

==en construction==

== Définition ==
XXXXXXXXX

== Français ==
''' XXXXXXXXX '''

== Anglais ==
''' State–action–reward–state–action'''

State–action–reward–state–action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. It was proposed by Rummery and Niranjan in a technical note[1] with the name "Modified Connectionist Q-Learning" (MCQ-L). The alternative name SARSA, proposed by Rich Sutton, was only mentioned as a footnote.
<small>

[https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action Source : Wikipedia Machine Learning ]

[[Catégorie:vocabulary]]
[[Catégorie:Wikipedia-IA‎]]