DEMONSTRATION-DRIVEN REINFORCEMENT LEARNING

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a reinforcement learning system to select actions to be performed by an agent interacting with an environment to perform a particular task. In one aspect, one of the methods includes obtainin...

Full description

Saved in:
Bibliographic Details
Main Authors SCHOLZ, Jonathan Karl, DAVCHEV, Todor Bozhinov, SUSHKOV, Oleg O
Format Patent
LanguageEnglish
French
German
Published 19.06.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a reinforcement learning system to select actions to be performed by an agent interacting with an environment to perform a particular task. In one aspect, one of the methods includes obtaining a training sequence comprising a respective training observations at each of a plurality of time steps; obtaining demonstration data comprising one or more demonstration sequences; generating a new training sequence from the training sequence and the demonstration data; and training the goal-conditioned policy neural network on the new training sequence through reinforcement learning.
Bibliography:Application Number: EP20220800203