Deepmind Technologies Limited

Fengning Ding

Oriol Vinyals

Tom Schaul

Andrew Zisserman

Joao Carreira

Simon Osindero

William Clinton Dabney

Felix George Hill

Georg Ostrovski

Carl Doersch

Diana Luiza Borsa

David Szepesvari

Andrew Kyle Lampinen

Aaditya K Singh

Jean-Baptiste Alayrac

Catalin-Dumitru Ionescu

Andrew Coulter Jaegle

Andrew Brock

Daniel Zoran

Evan Gerard Shelhamer

Olivier Jean Hénaff

Skanda Kumar Koppula

Sebastian Borgeaud Dit Avocat

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a speaker neural network using one or more listener neural networks.

Training a speaker neural network using one or more listener neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes sampling a behavior modulation in accordance with a current probability distribution; for each of one or more time steps: processing an input comprising an observation characterizing a current state of the environment at the time step using an action selection neural network to generate a respective action score for each action in a set of possible actions that can be performed by the agent; modifying the action scores using the sampled behavior modulation; and selecting the action to be performed by the agent at the time step based on the modified action scores; determining a fitness measure corresponding to the sampled behavior modulation; and updating the current probability distribution over the set of possible behavior modulations using the fitness measure corresponding to the behavior modulation.

Modulating agent behavior to optimize learning progress

Growing community of inventors

London, United Kingdom

Fengning Ding