-
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
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.
-
Patent Agency Ranking
公开(公告)号：US20240176045A1
公开(公告)日：2024-05-30
申请号：US18277729
申请日：2022-02-16
Applicant: DeepMind Technologies Limited
Inventor： Suman Ravuri , Karel Lenc , Piotr Wojciech Mirowski , Remi Roger Alain Paul Lam , Matthew James Willson , Andrew Brock
IPC: G01W1/10 , G06N3/0475
CPC classification number: G01W1/10 , G06N3/0475
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for precipitation nowcasting using generative neural networks. One of the methods includes obtaining a context temporal sequence of a plurality of context radar fields characterizing a real-world location, each context radar field characterizing the weather in the real-world location at a corresponding preceding time point; sampling a set of one or more latent inputs by sampling values from a specified distribution; and for each sampled latent input, processing the context temporal sequence of radar fields and the sampled latent input using a generative neural network that has been configured through training to process the temporal sequence of radar fields to generate as output a predicted temporal sequence comprising a plurality of predicted radar fields, each predicted radar field in the predicted temporal sequence characterizing the predicted weather in the real-world location at a corresponding future time point.
-
公开(公告)号：US11074481B2
公开(公告)日：2021-07-27
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
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：US20190266449A1
公开(公告)日：2019-08-29
申请号：US16403343
申请日：2019-05-03
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
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：US20240184982A1
公开(公告)日：2024-06-06
申请号：US18527211
申请日：2023-12-01
Applicant: DeepMind Technologies Limited
IPC: G06F40/20
CPC classification number: G06F40/20
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating long textual works using language model neural networks. For example, the textual works can be generated hierarchically by performing a hierarchy of generation steps using the same language model neural network.
-
公开(公告)号：US10572776B2
公开(公告)日：2020-02-25
申请号：US16403343
申请日：2019-05-03
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
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.
-
-
-
-
-
Search Results
6
records
(took 0.012 seconds)
