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...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | English French German |
Published |
19.06.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |