Patents by Inventor Saran Tunyasuvunakool

Saran Tunyasuvunakool 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).

  • CONTROLLING ROBOTS USING LATENT ACTION VECTOR CONDITIONED CONTROLLER NEURAL NETWORKS
    Publication number: 20250224737
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an agent can be controlled using a hierarchical controller that includes a task policy neural network and a low-level controller neural network.
    Type: Application
    Filed: March 27, 2023
    Publication date: July 10, 2025
    Inventors: Steven Bohez, Saran Tunyasuvunakool
  • Reinforcement and imitation learning for a task
    Patent number: 12343874
    Abstract: A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.
    Type: Grant
    Filed: April 25, 2023
    Date of Patent: July 1, 2025
    Assignee: DeepMind Technologies Limited
    Inventors: Saran Tunyasuvunakool, Yuke Zhu, Joshua Merel, János Kramár, Ziyu Wang, Nicolas Manfred Otto Heess
  • REINFORCEMENT AND IMITATION LEARNING FOR A TASK
    Publication number: 20230330848
    Abstract: A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.
    Type: Application
    Filed: April 25, 2023
    Publication date: October 19, 2023
    Inventors: Saran Tunyasuvunakool, Yuke Zhu, Joshua Merel, János Kramár, Ziyu Wang, Nicolas Manfred Otto Heess
  • REINFORCEMENT AND IMITATION LEARNING FOR A TASK
    Publication number: 20190126472
    Abstract: A neural network control system for controlling an agent to perform a task in a real-world environment, operates based on both image data and proprioceptive data describing the configuration of the agent. The training of the control system includes both imitation learning, using datasets generated from previous performances of the task, and reinforcement learning, based on rewards calculated from control data output by the control system.
    Type: Application
    Filed: October 29, 2018
    Publication date: May 2, 2019
    Inventors: Saran Tunyasuvunakool, Yuke Zhu, Joshua Merel, Janos Kramar, Ziyu Wang, Nicolas Manfred Otto Heess