Deepmind Technologies Limited

Cagdas Alcicek

Koray Kavukcuoglu

David Silver

Volodymyr Mnih

Mustafa Suleyman

Samuel Blackwell

Arun Sarath Nair

Vedavyas Panneershelvam

Alessandro De Maria

Praveen Deepak Srinivasan

Rory Fearon

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.

Distributed training of reinforcement learning systems

Growing community of inventors

London, United Kingdom

Cagdas Alcicek