Continuous control with deep reinforcement learning

US10776692B2 · kind B2 · utility

Assignee

• DeepMind Technologies Limited · GB

Inventors

• Timothy Paul Lillicrap · London, GB
• Jonathan James Hunt · London, GB
• Alexander Pritzel · London, GB
• Nicolas Manfred Otto Heess · London, GB
• Tom Erez · London, GB
• Yuval Tassa · London, GB
• David Silver · Hitchin, GB
• Daniel Pieter Wierstra · London, GB

Key dates

• Filing date: Jul 22, 2016
• Grant date: Sep 15, 2020
• Expiry date: Jul 17, 2039

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V10/82
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an actor neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining a minibatch of experience tuples; and updating current values of the parameters of the actor neural network, comprising: for each experience tuple in the minibatch: processing the training observation and the training action in the experience tuple using a critic neural network to determine a neural network output for the experience tuple, and determining a target neural network output for the experience tuple; updating current values of the parameters of the critic neural network using errors between the target neural network outputs and the neural network outputs; and updating the current values of the parameters of the actor neural network using the critic neural network.