TRAINING ACTION SELECTION NEURAL NETWORKS USING HINDSIGHT MODELLING

TRAINING ACTION SELECTION NEURAL NETWORKS USING HINDSIGHT MODELLING

A reinforcement learning method and system that selects actions to be performed by a reinforcement learning agent interacting with an environment. A causal model is implemented by a hindsight model neural network and trained using hindsight i.e. using future environment state trajectories. As the me...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: BUESING, Lars, VIOLA, Fabio, GUEZ, Arthur Clement, HEESS, Nicolas Manfred Otto, WEBER, Theophane Guillaume
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A reinforcement learning method and system that selects actions to be performed by a reinforcement learning agent interacting with an environment. A causal model is implemented by a hindsight model neural network and trained using hindsight i.e. using future environment state trajectories. As the method and system does not have access to this future information when selecting an action, the hindsight model neural network is used to train a model neural network which is conditioned on data from current observations, which learns to predict an output of the hindsight model neural network.