公开(公告)号：US20200151515A1

公开(公告)日：2020-05-14

申请号：US16745757

申请日：2020-01-17

Applicant: DeepMind Technologies Limited

Inventor： Fabio Viola ,  Piotr Wojciech Mirowski ,  Andrea Banino ,  Razvan Pascanu ,  Hubert Josef Soyer ,  Andrew James Ballard ,  Sudarshan Kumaran ,  Raia Thais Hadsell ,  Laurent Sifre ,  Rostislav Goroshin ,  Koray Kavukcuoglu ,  Misha Man Ray Denil

IPC: G06K9/62 ,  G06N3/00 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a geometry-prediction neural network, an intermediate output generated by the action selection policy neural network to predict a value of a feature of a geometry of the environment when in the current state; and backpropagating a gradient of a geometry-based auxiliary loss into the action selection policy neural network to determine a geometry-based auxiliary update for current values of the network parameters.

公开(公告)号：US20200090006A1

公开(公告)日：2020-03-19

申请号：US16689058

申请日：2019-11-19

Applicant: DeepMind Technologies Limited

Inventor： Daniel Pieter Wierstra ,  Yujia Li ,  Razvan Pascanu ,  Peter William Battaglia ,  Theophane Guillaume Weber ,  Lars Buesing ,  David Paul Reichert ,  Arthur Clement Guez ,  Danilo Jimenez Rezende ,  Adrià Puigdomènech Badia ,  Oriol Vinyals ,  Nicolas Manfred Otto Heess ,  Sebastien Henri Andre Racaniere

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/68

Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.