Patents by Inventor Peter William Battaglia
Peter William Battaglia 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).
-
Patent number: 12131243Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating data specifying a three-dimensional mesh of an object using an auto-regressive neural network.Type: GrantFiled: February 8, 2021Date of Patent: October 29, 2024Assignee: DeepMind Technologies LimitedInventors: Charlie Thomas Curtis Nash, Iaroslav Ganin, Seyed Mohammadali Eslami, Peter William Battaglia
-
Publication number: 20240176982Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network that includes one or more graph neural network layers. In one aspect, a method comprises: generating data defining a graph, comprising: generating a respective final feature representation for each node, wherein, for each of one or more of the nodes, the respective final feature representation is a modified feature representation that is generated from a respective feature representation for the node using respective noise; processing the data defining the graph using one or more of the graph neural network layers of the neural network to generate a respective updated node embedding of each node; and processing, for each of one or more of the nodes having modified feature representations, the updated node embedding of the node to generate a respective de-noising prediction for the node.Type: ApplicationFiled: May 30, 2022Publication date: May 30, 2024Inventors: Jonathan William Godwin, Peter William Battaglia, Kevin Michael Schaarschmidt, Alvaro Sanchez
-
Publication number: 20240104785Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating compressed representations of synthetic images. One of the methods is a method of generating a synthetic image using a generative neural network, and includes: generating, using the generative neural network, a plurality of coefficients that represent the synthetic image after the synthetic image has been encoded using a lossy compression algorithm; and decoding the synthetic image by applying the lossy compression algorithm to the plurality of coefficients.Type: ApplicationFiled: February 7, 2022Publication date: March 28, 2024Inventors: Charlie Thomas Curtis Nash, Peter William Battaglia
-
Publication number: 20230359788Abstract: This specification describes a simulation system that performs simulations of physical environments using a graph neural network. At each of one or more time steps in a sequence of time steps, the system can process a representation of a current state of the physical environment at the current time step using the graph neural network to generate a prediction of a next state of the physical environment at the next time step. Some implementations of the system are adapted for hardware GLOBAL acceleration. As well as performing simulations, the system can be used to predict physical quantities based on measured real-world data. Implementations of the system are differentiable and can also be used for design optimization, and for optimal control tasks.Type: ApplicationFiled: October 1, 2021Publication date: November 9, 2023Inventors: Alvaro Sanchez, Jonathan William Godwin, Rex Ying, Tobias Pfaff, Meire Fortunato, Peter William Battaglia
-
Publication number: 20230076437Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating data specifying a three-dimensional mesh of an object using an auto-regressive neural network.Type: ApplicationFiled: February 8, 2021Publication date: March 9, 2023Inventors: Charlie Thomas Curtis Nash, Iaroslav Ganin, Seyed Mohammadali Eslami, Peter William Battaglia
-
Publication number: 20220366247Abstract: A reinforcement learning system and method that selects actions to be performed by an agent interacting with an environment. The system uses a combination of reinforcement learning and a look ahead search: Reinforcement learning Q-values are used to guide the look ahead search and the search is used in turn to improve the Q-values. The system learns from a combination of real experience and simulated, model-based experience.Type: ApplicationFiled: September 23, 2020Publication date: November 17, 2022Inventors: Jessica Blake Chandler Hamrick, Victor Constant Bapst, Alvaro Sanchez, Tobias Pfaff, Theophane Guillaume Weber, Lars Buesing, Peter William Battaglia
-
Patent number: 11388424Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.Type: GrantFiled: December 29, 2020Date of Patent: July 12, 2022Assignee: DeepMind Technologies LimitedInventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
-
Patent number: 11328183Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.Type: GrantFiled: September 14, 2020Date of Patent: May 10, 2022Assignee: DeepMind Technologies LimitedInventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
-
Publication number: 20210192358Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting the actions of, or influences on, agents in environments with multiple agents, in particular for reinforcement learning. In one aspect, a relational forward model (RFM) system receives agent data representing agent actions for each of multiple agents and implements: an encoder graph neural network subsystem to process the agent data as graph data to provide encoded graph data, a recurrent graph neural network subsystem to process the encoded graph data to provide processed graph data, a decoder graph neural network subsystem to decode the processed graph data to provide decoded graph data and an output to provide representation data for node and/or edge attributes of the decoded graph data relating to a predicted action of one or more of the agents. A reinforcement learning system includes the RFM system.Type: ApplicationFiled: May 20, 2019Publication date: June 24, 2021Inventors: Hasuk Song, Andrea Tacchetti, Peter William Battaglia, Vinicius Zambaldi
-
Publication number: 20210152835Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.Type: ApplicationFiled: December 29, 2020Publication date: May 20, 2021Inventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
-
Publication number: 20210089834Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.Type: ApplicationFiled: December 7, 2020Publication date: March 25, 2021Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
-
Publication number: 20210073594Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.Type: ApplicationFiled: September 14, 2020Publication date: March 11, 2021Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
-
Publication number: 20210049467Abstract: A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an input graph e.g. the static and dynamic graphs, to provide an output graph, e.g. a predicted dynamic graph. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning. The trained graph neural network system can be applied to physical systems with similar but new graph structures (zero-shot learning).Type: ApplicationFiled: April 12, 2019Publication date: February 18, 2021Inventors: Martin Riedmiller, Raia Thais Hadsell, Peter William Battaglia, Joshua Merel, Jost Tobias Springenberg, Alvaro Sanchez, Nicolas Manfred Otto Heess
-
Patent number: 10887607Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.Type: GrantFiled: November 18, 2019Date of Patent: January 5, 2021Assignee: DeepMind Technologies LimitedInventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
-
Patent number: 10860895Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.Type: GrantFiled: November 19, 2019Date of Patent: December 8, 2020Assignee: DeepMind Technologies LimitedInventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
-
Patent number: 10776670Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.Type: GrantFiled: November 19, 2019Date of Patent: September 15, 2020Assignee: DeepMind Technologies LimitedInventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
-
Publication number: 20200092565Abstract: A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.Type: ApplicationFiled: November 18, 2019Publication date: March 19, 2020Inventors: Nicholas Watters, Razvan Pascanu, Peter William Battaglia, Daniel Zorn, Theophane Guillaume Weber
-
Publication number: 20200090006Abstract: A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.Type: ApplicationFiled: November 19, 2019Publication date: March 19, 2020Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Arthur Clement Guez, Danilo Jimenez Rezende, Adrià Puigdomènech Badia, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere
-
Publication number: 20200082227Abstract: A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.Type: ApplicationFiled: November 19, 2019Publication date: March 12, 2020Inventors: Daniel Pieter Wierstra, Yujia Li, Razvan Pascanu, Peter William Battaglia, Theophane Guillaume Weber, Lars Buesing, David Paul Reichert, Oriol Vinyals, Nicolas Manfred Otto Heess, Sebastien Henri Andre Racaniere