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

WO2018142378A1 MEMORY AUGMENTED GENERATIVE TEMPORAL MODELS 审中-公开
公开(公告)号：WO2018142378A1
公开(公告)日：2018-08-09
申请号：PCT/IB2018/050742
申请日：2018-02-06
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： WAYNE, Gregory Duncan , HUNG, Chia-Chun , GEMICI, Mevlana Celaleddin , SANTORO, Adam Anthony
IPC分类号： G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating sequences of predicted observations, for example images. In one aspect, a system comprises a controller recurrent neural network, and a decoder neural network to process a set of latent variables to generate an observation. An external memory and a memory interface subsystem is configured to, for each of a plurality of time steps, receive an updated hidden state from the controller, generate a memory context vector by reading data from the external memory using the updated hidden state, determine a set of latent variables from the memory context vector, generate a predicted observation by providing the set of latent variables to the decoder neural network, write data to the external memory using the latent variables, the updated hidden state, or both, and generate a controller input for a subsequent time step from the latent variables.

2. 发明申请

WO2020074741A1 CONTROLLING AGENTS OVER LONG TIME SCALES USING TEMPORAL VALUE TRANSPORT 审中-公开
公开(公告)号：WO2020074741A1
公开(公告)日：2020-04-16
申请号：PCT/EP2019/077704
申请日：2019-10-14
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： WAYNE, Gregory Duncan , LILLICRAP, Timothy Paul , HUNG, Chia-Chun , ABRAMSON, Joshua Simon
IPC分类号： G06N3/08 , G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task, One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.

3. 发明申请

WO2019170905A1 TRAINING AN UNSUPERVISED MEMORY-BASED PREDICTION SYSTEM TO LEARN COMPRESSED REPRESENTATIONS OF AN ENVIRONMENT 审中-公开
公开(公告)号：WO2019170905A1
公开(公告)日：2019-09-12
申请号：PCT/EP2019/055950
申请日：2019-03-11
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： WAYNE, Gregory Duncan , HUNG, Chia-Chun , AMOS, David Antony , MIRZA MOHAMMADI, Mehdi , AHUJA, Arun , LILLICRAP, Timothy Paul
IPC分类号： G06N3/00 , G06N3/04 , G06N3/08 , G06N7/00
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a memory-based prediction system configured to receive an input observation characterizing a state of an environment interacted with by an agent and to process the input observation and data read from a memory to update data stored in the memory and to generate a latent representation of the state of the environment. The method comprises: for each of a plurality of time steps: processing an observation for the time step and data read from the memory to: (i) update the data stored in the memory, and (ii) generate a latent representation of the current state of the environment as of the time step; and generating a predicted return that will be received by the agent as a result of interactions with the environment after the observation for the time step is received.

4. 发明申请

WO2022167625A1 IMITATION LEARNING BASED ON PREDICTION OF OUTCOMES 审中-公开
公开(公告)号：WO2022167625A1
公开(公告)日：2022-08-11
申请号：PCT/EP2022/052792
申请日：2022-02-04
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： JAEGLE, Andrew Coulter , SULSKY, Yury , WAYNE, Gregory Duncan , FERGUS, Robert David
IPC分类号： G06N3/08 , G06N3/04
摘要： A method is proposed of training a policy model to generate action data for controlling an agent to perform a task in an environment. The method comprises: obtaining, for each of a plurality of performances of the task, a corresponding demonstrator trajectory comprising a plurality of sets of state data characterizing the environment at each of a plurality of corresponding successive time steps during the performance of the task; using the demonstrator trajectories to generate a demonstrator model, the demonstrator model being operative to generate, for any said demonstrator trajectory, a value indicative of the probability of the demonstrator trajectory occurring; and jointly training an imitator model and a policy model. The joint training is performed by: generating a plurality of imitation trajectories, each imitation trajectory being generated by repeatedly receiving state data indicating a state of the environment, using the policy model to generate action data indicative of an action, and causing the action to be performed by the agent; training the imitator model using the imitation trajectories, the imitator model being operative to generate, for any said imitation trajectory, a value indicative of the probability of the imitation trajectory occurring; and training the policy model using a reward function which is a measure of the similarity of the demonstrator model and the imitator model.

5. 发明申请

WO2018211140A1 DATA EFFICIENT IMITATION OF DIVERSE BEHAVIORS 审中-公开
公开(公告)号：WO2018211140A1
公开(公告)日：2018-11-22
申请号：PCT/EP2018/063281
申请日：2018-05-22
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： WAYNE, Gregory Duncan , MEREL, Joshua , WANG, Ziyu , HEESS, Nicolas Manfred Otto , FREITAS, Joao Ferdinando , REED, Scott Ellison
IPC分类号： G06N3/04 , G06N3/08 , G06N3/00
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes: obtaining data identifying a set of trajectories, each trajectory comprising a set of observations characterizing a set of states of the environment and corresponding actions performed by another agent in response to the states; obtaining data identifying an encoder that maps the observations onto embeddings for use in determining a set of imitation trajectories; determining, for each trajectory, a corresponding embedding by applying the encoder to the trajectory; determining a set of imitation trajectories by applying a policy defined by the neural network to the embedding for each trajectory; and adjusting parameters of the neural network based on the set of trajectories, the set of imitation trajectories and the embeddings.

7. 发明公开

EP4272131A1 IMITATION LEARNING BASED ON PREDICTION OF OUTCOMES 审中-实审
公开(公告)号：EP4272131A1
公开(公告)日：2023-11-08
申请号：EP22707626.2
申请日：2022-02-04
申请人： DeepMind Technologies Limited
发明人： JAEGLE, Andrew Coulter , SULSKY, Yury , WAYNE, Gregory Duncan , FERGUS, Robert David
IPC分类号： G06N3/08 , G06N3/04

8. 发明公开

EP3698284A1 TRAINING AN UNSUPERVISED MEMORY-BASED PREDICTION SYSTEM TO LEARN COMPRESSED REPRESENTATIONS OF AN ENVIRONMENT 审中-实审
公开(公告)号：EP3698284A1
公开(公告)日：2020-08-26
申请号：EP19710392.2
申请日：2019-03-11
申请人： DeepMind Technologies Limited
发明人： WAYNE, Gregory Duncan , HUNG, Chia-Chun , AMOS, David Antony , MIRZA MOHAMMADI, Mehdi , AHUJA, Arun , LILLICRAP, Timothy Paul
IPC分类号： G06N3/00 , G06N3/04 , G06N3/08 , G06N7/00

9. 发明公开

EP3566182A1 MEMORY AUGMENTED GENERATIVE TEMPORAL MODELS 审中-实审
公开(公告)号：EP3566182A1
公开(公告)日：2019-11-13
申请号：EP18708482.7
申请日：2018-02-06
申请人： Deepmind Technologies Limited
发明人： WAYNE, Gregory Duncan , HUNG, Chia-Chun , GEMICI, Mevlana Celaleddin , SANTORO, Adam Anthony
IPC分类号： G06N3/04

10. 发明公开

EP3864581A1 CONTROLLING AGENTS OVER LONG TIME SCALES USING TEMPORAL VALUE TRANSPORT 审中-实审
公开(公告)号：EP3864581A1
公开(公告)日：2021-08-18
申请号：EP19787232.8
申请日：2019-10-14
申请人： DeepMind Technologies Limited
发明人： WAYNE, Gregory Duncan , LILLICRAP, Timothy Paul , HUNG, Chia-Chun , ABRAMSON, Joshua Simon
IPC分类号： G06N3/08 , G06N3/04

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