专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2021048434A1 DATA-DRIVEN ROBOT CONTROL 审中-公开
公开(公告)号：WO2021048434A1
公开(公告)日：2021-03-18
申请号：PCT/EP2020/075609
申请日：2020-09-14
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： CABI, Serkan , WANG, Ziyu , NOVIKOV, Alexander , KONYUSHKOVA, Ksenia , COLMENAREJO, Sergio Gomez , REED, Scott Ellison , DENIL, Misha Man Ray , SCHOLZ, Jonathan Karl , SUSHKOV, Oleg O. , JEONG, Rae Chan , BARKER, David , BUDDEN, David , VECERIK, Mel , AYTAR, Yusuf , GOMES DE FREITAS, Joao Ferdinando
IPC分类号： G06N3/00 , G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.

2. 发明申请

WO2021009293A1 TRAINING A NEURAL NETWORK TO CONTROL AN AGENT USING TASK-RELEVANT ADVERSARIAL IMITATION LEARNING 审中-公开
公开(公告)号：WO2021009293A1
公开(公告)日：2021-01-21
申请号：PCT/EP2020/070164
申请日：2020-07-16
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： ZOLNA, Konrad , REED, Scott Ellison , WANG, Ziyu , NOVIKOV, Alexander , COLMENAREJO, Sergio Gomez , GOMES DE FREITAS, Joao Ferdinando , BUDDEN, David , CABI, Serkan
IPC分类号： G06N3/00 , G06N3/04 , B25J9/16 , G06N3/08
摘要： A method is proposed of training a neural network to generate action data for controlling an agent to perform a task in an environment. The method includes obtaining, for each of a plurality of performances of the task, one or more first tuple datasets, each first tuple dataset comprising state data characterizing a state of the environment at a corresponding time during the performance of the task; and a concurrent process of training the neural network and a discriminator network. The training process comprises a plurality of neural network update steps and a plurality of discriminator network update steps. Each neural network update step comprises: receiving state data characterizing a current state of the environment; using the neural network and the state data to generate action data indicative of an action to be performed by the agent; forming a second tuple dataset comprising the state data; using the second tuple dataset to generate a reward value, wherein the reward value comprises an imitation value generated by the discriminator network based on the second tuple dataset; and updating one or more parameters of the neural network based on the reward value. Each discriminator network update step comprises updating the discriminator network based on a plurality of the first tuple datasets and a plurality of the second tuple datasets, the update being to increase respective imitation values which the discriminator network generates upon receiving any of the plurality of the first tuple datasets compared to respective imitation values which the discriminator network generates upon receiving any of the plurality of the second tuple datasets. The updating process is performed subject to a constraint that the updated discriminator network, upon receiving any of at least a certain proportion of a first subset of the first tuple datasets and/or any of at least a certain proportion of a second subset of the second tuple datasets, does not generate imitation values which correctly indicate that those tuple datasets are first or second tuple datasets.

3. 发明申请

WO2023025607A1 AUTOREGRESSIVELY GENERATING SEQUENCES OF DATA ELEMENTS DEFINING ACTIONS TO BE PERFORMED BY AN AGENT 审中-公开
公开(公告)号：WO2023025607A1
公开(公告)日：2023-03-02
申请号：PCT/EP2022/072731
申请日：2022-08-12
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： REED, Scott Ellison , ZOLNA, Konrad , PARISOTTO, Emilio , EREZ, Tom , NOVIKOV, Alexander , RAE, Jack William , DENIL, Misha Man Ray , GOMES DE FREITAS, Joao Ferdinando , VINYALS, Oriol , GOMEZ, Sergio , EDWARDS, Ashley Deloris , BRUCE, Jacob , BARTH-MARON, Gabriel
IPC分类号： G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent to interact with an environment using an action selection neural network. In one aspect, a method comprises, at each time step in a sequence of time steps: generating a current representation of a state of a task being performed by the agent in the environment as of the current time step as a sequence of data elements; autoregressively generating a sequence of data elements representing a current action to be performed by the agent at the current time step; and after autoregressively generating the sequence of data elements representing the current action, causing the agent to perform the current action at the current time step.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式