Serveur d'exploration sur Pittsburgh

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Eléments de l'association

France822
Alessandro Lazaric6
France Sauf Alessandro Lazaric" 816
Alessandro Lazaric Sauf France" 0
France Et Alessandro Lazaric 6
France Ou Alessandro Lazaric 822
Corpus20845
\n\n\n\n \n

List of bibliographic references

Number of relevant bibliographic references: 6.
Ident.Authors (with country if any)Title
000047 Akram Erraqabi [France] ; Alessandro Lazaric [France] ; Michal Valko [France] ; Emma Brunskill [États-Unis] ; Yun-En Liu [États-Unis]Trading off rewards and errors in multi-armed bandits
000157 Akram Erraqabi [France] ; Alessandro Lazaric [France] ; Michal Valko [France] ; Emma Brunskill [États-Unis] ; Yun-En Liu [États-Unis]Rewards and errors in multi-arm bandits for interactive education
000188 Jessica Chemali [États-Unis] ; Alessandro Lazaric [France]Direct Policy Iteration with Demonstrations
000709 Mohammad Gheshlaghi Azar [France] ; Alessandro Lazaric [France] ; Emma Brunskill [États-Unis]Online Stochastic Optimization under Correlated Bandit Feedback
005A09 Mohammad Gheshlaghi Azar [États-Unis] ; Alessandro Lazaric [France] ; Emma Brunskill [États-Unis]Sequential Transfer in Multi-armed Bandit with Finite Set of Models
005A25 Mohammad Gheshlaghi Azar [États-Unis] ; Alessandro Lazaric [France] ; Emma Brunskill [États-Unis]Regret Bounds for Reinforcement Learning with Policy Advice

Wicri

This area was generated with Dilib version V0.6.38.
Data generation: Fri Jun 18 17:37:45 2021. Site generation: Fri Jun 18 18:15:47 2021