Patents by Inventor David Constantine Patrick Warde-Farley
David Constantine Patrick Warde-Farley has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240160901Abstract: 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. One of the methods includes receiving a current observation; processing the current observation using a proposal neural network to generate a proposal output that defines a proposal probability distribution over a set of possible actions that can be performed by the agent to interact with the environment; sampling (i) one or more actions from the set of possible actions in accordance with the proposal probability distribution and (ii) one or more actions randomly from the set of possible actions; processing the current observation and each sampled action using a Q neural network to generate a Q value; and selecting an action using the Q values generated by the Q neural network.Type: ApplicationFiled: January 8, 2024Publication date: May 16, 2024Inventors: Tom Van de Wiele, Volodymyr Mnih, Andriy Mnih, David Constantine Patrick Warde-Farley
-
Patent number: 11868866Abstract: 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. One of the methods includes receiving a current observation; processing the current observation using a proposal neural network to generate a proposal output that defines a proposal probability distribution over a set of possible actions that can be performed by the agent to interact with the environment; sampling (i) one or more actions from the set of possible actions in accordance with the proposal probability distribution and (ii) one or more actions randomly from the set of possible actions; processing the current observation and each sampled action using a Q neural network to generate a Q value; and selecting an action using the Q values generated by the Q neural network.Type: GrantFiled: November 18, 2019Date of Patent: January 9, 2024Assignee: Deep Mind Technologies LimitedInventors: Tom Van de Wiele, Volodymyr Mnih, Andriy Mnih, David Constantine Patrick Warde-Farley
-
Publication number: 20230325635Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network for use in controlling an agent using relative variational intrinsic control. In one aspect, a method includes: selecting a skill from a set of skills; generating a trajectory by controlling the agent using the policy neural network while the policy neural network is conditioned on the selected skill; processing an initial observation and a last observation using a relative discriminator neural network to generate a relative score; processing the last observation using an absolute discriminator neural network to generate an absolute score; generating a reward for the trajectory from the absolute score corresponding to the selected skill and the relative score corresponding to the selected skill; and training the policy neural network on the reward for the trajectory.Type: ApplicationFiled: September 10, 2021Publication date: October 12, 2023Inventors: David Constantine Patrick Warde-Farley, Steven Stenberg Hansen, Volodymyr Mnih, Kate Alexandra Baumli
-
Patent number: 11727281Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent that interacts with an environment. In one aspect, a system comprises: an action selection subsystem that selects actions to be performed by the agent using an action selection policy generated using an action selection neural network; a reward subsystem that is configured to: receive an observation characterizing a current state of the environment and an observation characterizing a goal state of the environment; generate a reward using an embedded representation of the observation characterizing the current state of the environment and an embedded representation of the observation characterizing the goal state of the environment; and a training subsystem that is configured to train the action selection neural network based on the rewards generated by the reward subsystem using reinforcement learning techniques.Type: GrantFiled: January 27, 2022Date of Patent: August 15, 2023Assignee: DeepMind Technologies LimitedInventors: David Constantine Patrick Warde-Farley, Volodymyr Mnih
-
Publication number: 20220164673Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent that interacts with an environment. In one aspect, a system comprises: an action selection subsystem that selects actions to be performed by the agent using an action selection policy generated using an action selection neural network; a reward subsystem that is configured to: receive an observation characterizing a current state of the environment and an observation characterizing a goal state of the environment; generate a reward using an embedded representation of the observation characterizing the current state of the environment and an embedded representation of the observation characterizing the goal state of the environment; and a training subsystem that is configured to train the action selection neural network based on the rewards generated by the reward subsystem using reinforcement learning techniques.Type: ApplicationFiled: January 27, 2022Publication date: May 26, 2022Inventors: David Constantine Patrick Warde-Farley, Volodymyr Mnih
-
Patent number: 11263531Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent that interacts with an environment. In one aspect, a system comprises: an action selection subsystem that selects actions to be performed by the agent using an action selection policy generated using an action selection neural network; a reward subsystem that is configured to: receive an observation characterizing a current state of the environment and an observation characterizing a goal state of the environment; generate a reward using an embedded representation of the observation characterizing the current state of the environment and an embedded representation of the observation characterizing the goal state of the environment; and a training subsystem that is configured to train the action selection neural network based on the rewards generated by the reward subsystem using reinforcement learning techniques.Type: GrantFiled: May 20, 2019Date of Patent: March 1, 2022Assignee: DeepMind Technologies LimitedInventors: David Constantine Patrick Warde-Farley, Volodymyr Mnih
-
Publication number: 20210357731Abstract: 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. One of the methods includes receiving a current observation; processing the current observation using a proposal neural network to generate a proposal output that defines a proposal probability distribution over a set of possible actions that can be performed by the agent to interact with the environment; sampling (i) one or more actions from the set of possible actions in accordance with the proposal probability distribution and (ii) one or more actions randomly from the set of possible actions; processing the current observation and each sampled action using a Q neural network to generate a Q value; and selecting an action using the Q values generated by the Q neural network.Type: ApplicationFiled: November 18, 2019Publication date: November 18, 2021Inventors: Tom Van de Wiele, Volodymyr Mnih, Andriy Mnih, David Constantine Patrick Warde-Farley
-
Publication number: 20190354869Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent that interacts with an environment. In one aspect, a system comprises: an action selection subsystem that selects actions to be performed by the agent using an action selection policy generated using an action selection neural network; a reward subsystem that is configured to: receive an observation characterizing a current state of the environment and an observation characterizing a goal state of the environment; generate a reward using an embedded representation of the observation characterizing the current state of the environment and an embedded representation of the observation characterizing the goal state of the environment; and a training subsystem that is configured to train the action selection neural network based on the rewards generated by the reward subsystem using reinforcement learning techniques.Type: ApplicationFiled: May 20, 2019Publication date: November 21, 2019Inventors: David Constantine Patrick Warde-Farley, Volodymyr Mnih