UCB Momentum Q-learning: Correcting the bias without forgetting

Ménard, Pierre; Domingues, Omar; Shang, Xuedong; Valko, Michal

Type de document :

Communication dans un congrès avec actes

Titre :

UCB Momentum Q-learning: Correcting the bias without forgetting

Auteur(s) :

Ménard, Pierre [Auteur]
Otto-von-Guericke-Universität Magdeburg = Otto-von-Guericke University [Magdeburg] [OVGU]
Domingues, Omar [Auteur]
Scool [Scool]
Shang, Xuedong [Auteur]
Scool [Scool]
Valko, Michal [Auteur]

DeepMind [Paris]

Titre de la manifestation scientifique :

International Conference on Machine Learning

Ville :

Vienna / Virtual

Pays :

Autriche

Date de début de la manifestation scientifique :

2021-07-18

Discipline(s) HAL :

Statistiques [stat]/Machine Learning [stat.ML]

Résumé en anglais : [en]

We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stagedependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add ...
Lire la suite >We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algorithm for reinforcement learning in tabular and possibly stagedependent, episodic Markov decision process. UCBMQ is based on Q-learning where we add a momentum term and rely on the principle of optimism in face of uncertainty to deal with exploration. Our new technical ingredient of UCBMQ is the use of momentum to correct the bias that Q-learning suffers while, at the same time, limiting the impact it has on the the second-order term of the regret. For UCBMQ, we are able to guarantee a regret of at most O(√ H 3 SAT + H 4 SA) where H is the length of an episode, S the number of states, A the number of actions, T the number of episodes and ignoring terms in poly log(SAHT). Notably, UCBMQ is the first algorithm that simultaneously matches the lower bound of Ω(√ H 3 SAT) for large enough T and has a second-order term (with respect to the horizon T) that scales only linearly with the number of states S.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

https://hal.inria.fr/hal-03289033/document
Accès libre
Accéder au document

https://hal.inria.fr/hal-03289033/document
Accès libre
Accéder au document

https://hal.inria.fr/hal-03289033/document
Accès libre
Accéder au document

document
Accès libre
Accéder au document

menard2021ucb.pdf
Accès libre
Accéder au document

document
Accès libre
Accéder au document

menard2021ucb.pdf
Accès libre
Accéder au document

UCB Momentum Q-learning: Correcting the ... BibTeX CSV Excel RIS

Fichiers

UCB Momentum Q-learning: Correcting the ...

BibTeX

CSV

Excel

RIS