-
1.
公开(公告)号:US20250093828A1
公开(公告)日:2025-03-20
申请号:US18892260
申请日:2024-09-20
Applicant: DeepMind Technologies Limited
Inventor: Arun Ahuja , Robert David Fergus , Ishita Dasgupta , Kavya Venkata Kota Sai Kopparapu
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a high-level controller neural network for controlling an agent. In particular, the high-level controller neural network generates natural language commands that can be provided as input to a low-level controller neural network, which generates control outputs that can be used to control the agent.
-
公开(公告)号:US20250051289A1
公开(公告)日:2025-02-13
申请号:US18929321
申请日:2024-10-28
Applicant: DeepMind Technologies Limited
Inventor: Gregory Duncan Wayne , Chia-Chun Hung , David Antony Amos , Mehdi Mirza Mohammadi , Arun Ahuja , Timothy Paul Lillicrap
IPC: C07D239/47 , A61P35/00 , C07C275/36
Abstract: 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.
-
公开(公告)号:US12159221B2
公开(公告)日:2024-12-03
申请号:US16766945
申请日:2019-03-11
Applicant: DeepMind Technologies Limited
Inventor: Gregory Duncan Wayne , Chia-Chun Hung , David Antony Amos , Mehdi Mirza Mohammadi , Arun Ahuja , Timothy Paul Lillicrap
Abstract: 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.
-
公开(公告)号:US20240112038A1
公开(公告)日:2024-04-04
申请号:US18475157
申请日:2023-09-26
Applicant: DeepMind Technologies Limited
Inventor: Ishita Dasgupta , Shiqi Chen , Kenneth Daniel Marino , Wenling Shang , Arun Ahuja
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using reporter neural networks.
-
公开(公告)号:US20230178076A1
公开(公告)日:2023-06-08
申请号:US18077194
申请日:2022-12-07
Applicant: DeepMind Technologies Limited
Inventor: Joshua Simon Abramson , Arun Ahuja , Federico Javier Carnevale , Petko Ivanov Georgiev , Chia-Chun Hung , Timothy Paul Lillicrap , Alistair Michael Muldal , Adam Anthony Santoro , Tamara Louise von Glehn , Jessica Paige Landon , Gregory Duncan Wayne , Chen Yan , Rui Zhu
IPC: G10L15/22 , G10L15/16 , G10L13/02 , G06V10/82 , G06V20/50 , G06F40/284 , G06F40/40 , G06V10/774 , G10L15/06
CPC classification number: G10L15/22 , G10L15/16 , G10L13/02 , G06V10/82 , G06V20/50 , G06F40/284 , G06F40/40 , G06V10/774 , G10L15/063 , G10L2015/223
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an interactive agent can be controlled based on multi-modal inputs that include both an observation image and a natural language text sequence.
-
公开(公告)号:US20210034969A1
公开(公告)日:2021-02-04
申请号:US16766945
申请日:2019-03-11
Applicant: DeepMind Technologies Limited
Inventor: Gregory Duncan Wayne , Chia-Chun Hung , David Antony Amos , Mehdi Mirza Mohammadi , Arun Ahuja , Timothy Paul Lillicrap
Abstract: 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.
-
-
-
-
-