公开(公告)号：US20210089908A1

公开(公告)日：2021-03-25

申请号：US17032562

申请日：2020-09-25

Applicant: DeepMind Technologies Limited

Inventor： Tom Schaul ,  Diana Luiza Borsa ,  Fengning Ding ,  David Szepesvari ,  Georg Ostrovski ,  Simon Osindero ,  William Clinton Dabney

IPC: G06N3/08 ,  G06K9/62

Abstract: 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.

公开(公告)号：US12061964B2

公开(公告)日：2024-08-13

申请号：US17032562

申请日：2020-09-25

Applicant: DeepMind Technologies Limited

Inventor： Tom Schaul ,  Diana Luiza Borsa ,  Fengning Ding ,  David Szepesvari ,  Georg Ostrovski ,  Simon Osindero ,  William Clinton Dabney

IPC: G06N3/006 ,  G06F18/214 ,  G06F18/2415 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V40/20

CPC classification number: G06N3/006 ,  G06F18/2148 ,  G06F18/2415 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06V40/20

Abstract: 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.