Nicolas Manfred Otto Heess

Person

London, GB

People

Patents Grantslast 30 patents

Information Patent Grant
Training action selection neural networks using off-policy actor cr...
- Patent number 12,190,223
- Issue date Jan 7, 2025
- DeepMind Technologies Limited
- Ziyu Wang
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Multi-task neural network systems with task-specific policies and a...
- Patent number 11,983,634
- Issue date May 14, 2024
- DeepMind Technologies Limited
- Razvan Pascanu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training action selection neural networks using apprenticeship
- Patent number 11,886,997
- Issue date Jan 30, 2024
- DeepMind Technologies Limited
- Olivier Pietquin
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Selecting reinforcement learning actions using a low-level controller
- Patent number 11,875,258
- Issue date Jan 16, 2024
- DeepMind Technologies Limited
- Nicolas Manfred Otto Heess
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training action selection neural networks using apprenticeship
- Patent number 11,868,882
- Issue date Jan 9, 2024
- DeepMind Technologies Limited
- Olivier Claude Pietquin
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Continuous control with deep reinforcement learning
- Patent number 11,803,750
- Issue date Oct 31, 2023
- DeepMind Technologies Limited
- Timothy Paul Lillicrap
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Data-efficient reinforcement learning for continuous control tasks
- Patent number 11,741,334
- Issue date Aug 29, 2023
- DeepMind Technologies Limited
- Martin Riedmiller
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Neural networks for selecting actions to be performed by a robotic...
- Patent number 11,534,911
- Issue date Dec 27, 2022
- DeepMind Technologies Limited
- Razvan Pascanu
- G05 - CONTROLLING REGULATING
Information Patent Grant
Training action selection neural networks using apprenticeship
- Patent number 11,468,321
- Issue date Oct 11, 2022
- DeepMind Technologies Limited
- Olivier Claude Pietquin
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Imagination-based agent neural networks
- Patent number 11,328,183
- Issue date May 10, 2022
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Selecting reinforcement learning actions using a low-level controller
- Patent number 11,210,585
- Issue date Dec 28, 2021
- DeepMind Technologies Limited
- Nicolas Manfred Otto Heess
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Multi-task neural network systems with task-specific policies and a...
- Patent number 11,132,609
- Issue date Sep 28, 2021
- DeepMind Technologies Limited
- Razvan Pascanu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Imagination-based agent neural networks
- Patent number 10,860,895
- Issue date Dec 8, 2020
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Imagination-based agent neural networks
- Patent number 10,776,670
- Issue date Sep 15, 2020
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Continuous control with deep reinforcement learning
- Patent number 10,776,692
- Issue date Sep 15, 2020
- DeepMind Technologies Limited
- Timothy Paul Lillicrap
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training action selection neural networks using off-policy actor cr...
- Patent number 10,706,352
- Issue date Jul 7, 2020
- DeepMind Technologies Limited
- Ziyu Wang
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Data-efficient reinforcement learning for continuous control tasks
- Patent number 10,664,725
- Issue date May 26, 2020
- DeepMind Technologies Limited
- Martin Riedmiller
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Neural networks for selecting actions to be performed by a robotic...
- Patent number 10,632,618
- Issue date Apr 28, 2020
- DeepMind Technologies Limited
- Razvan Pascanu
- G06 - COMPUTING CALCULATING COUNTING

Patents Applicationslast 30 patents

Information Patent Application
NEURAL POPULATION LEARNING
- Publication number 20240412072
- Publication date Dec 12, 2024
- DeepMind Technologies Limited
- Siqi Liu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
HIERARCHICAL LATENT MIXTURE POLICIES FOR AGENT CONTROL
- Publication number 20240403652
- Publication date Dec 5, 2024
- DeepMind Technologies Limited
- Dushyant ` Rao
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
CONTROLLING AGENTS USING SUB-GOALS GENERATED BY LANGUAGE MODEL NEUR...
- Publication number 20240311617
- Publication date Sep 19, 2024
- DeepMind Technologies Limited
- Norman Di Palo
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
PLANNING USING A JUMPY TRAJECTORY DECODER NEURAL NETWORK
- Publication number 20240220795
- Publication date Jul 4, 2024
- DeepMind Technologies Limited
- Jingwei Zhang
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING
- Publication number 20240177002
- Publication date May 30, 2024
- DeepMind Technologies Limited
- Timothy Paul Lillicrap
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS
- Publication number 20240062035
- Publication date Feb 22, 2024
- DeepMind Technologies Limited
- Martin Riedmiller
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
REINFORCEMENT AND IMITATION LEARNING FOR A TASK
- Publication number 20230330848
- Publication date Oct 19, 2023
- DeepMind Technologies Limited
- Saran Tunyasuvunakool
- B25 - HAND TOOLS PORTABLE POWER-DRIVEN TOOLS MANIPULATORS
Information Patent Application
TRAINING AN ACTION SELECTION SYSTEM USING RELATIVE ENTROPY Q-LEARNING
- Publication number 20230214649
- Publication date Jul 6, 2023
- DeepMind Technologies Limited
- Rae Chan Jeong
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING ACTION SELECTION NEURAL NETWORKS USING APPRENTICESHIP
- Publication number 20230023189
- Publication date Jan 26, 2023
- DeepMind Technologies Limited
- Olivier Pietquin
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING ACTION SELECTION NEURAL NETWORKS USING HINDSIGHT MODELLING
- Publication number 20220366245
- Publication date Nov 17, 2022
- DeepMind Technologies Limited
- Arthur Clement Guez
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
NEURAL NETWORKS FOR SELECTING ACTIONS TO BE PERFORMED BY A ROBOTIC...
- Publication number 20220355472
- Publication date Nov 10, 2022
- DeepMind Technologies Limited
- Razvan Pascanu
- B25 - HAND TOOLS PORTABLE POWER-DRIVEN TOOLS MANIPULATORS
Information Patent Application
HIERARCHICAL POLICIES FOR MULTITASK TRANSFER
- Publication number 20220237488
- Publication date Jul 28, 2022
- DeepMind Technologies Limited
- Markus Wulfmeier
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
MULTI-TASK NEURAL NETWORK SYSTEMS WITH TASK-SPECIFIC POLICIES AND A...
- Publication number 20220083869
- Publication date Mar 17, 2022
- DeepMind Technologies Limited
- Razvan Pascanu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
IMAGINATION-BASED AGENT NEURAL NETWORKS
- Publication number 20210089834
- Publication date Mar 25, 2021
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
IMAGINATION-BASED AGENT NEURAL NETWORKS
- Publication number 20210073594
- Publication date Mar 11, 2021
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS
- Publication number 20210049467
- Publication date Feb 18, 2021
- DeepMind Technologies Limited
- Martin Riedmiller
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING
- Publication number 20200410351
- Publication date Dec 31, 2020
- DeepMind Technologies Limited
- Timothy Paul Lillicrap
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING ACTION SELECTION NEURAL NETWORKS USING OFF-POLICY ACTOR CR...
- Publication number 20200293862
- Publication date Sep 17, 2020
- DeepMind Technologies Limited
- Ziyu Wang
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS
- Publication number 20200285909
- Publication date Sep 10, 2020
- DeepMind Technologies Limited
- Martin Riedmiller
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
NEURAL NETWORKS FOR SELECTING ACTIONS TO BE PERFORMED BY A ROBOTIC...
- Publication number 20200223063
- Publication date Jul 16, 2020
- DeepMind Technologies Limited
- Razvan Pascanu
- B25 - HAND TOOLS PORTABLE POWER-DRIVEN TOOLS MANIPULATORS
Information Patent Application
TRAINING ACTION SELECTION NEURAL NETWORKS USING APPRENTICESHIP
- Publication number 20200151562
- Publication date May 14, 2020
- DeepMind Technologies Limited
- Olivier Pietquin
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
DATA EFFICIENT IMITATION OF DIVERSE BEHAVIORS
- Publication number 20200090042
- Publication date Mar 19, 2020
- DeepMind Technologies Limited
- Gregory Duncan Wayne
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
MULTI-TASK NEURAL NETWORK SYSTEMS WITH TASK-SPECIFIC POLICIES AND A...
- Publication number 20200090048
- Publication date Mar 19, 2020
- DeepMind Technologies Limited
- Razvan Pascanu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
IMAGINATION-BASED AGENT NEURAL NETWORKS
- Publication number 20200090006
- Publication date Mar 19, 2020
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
IMAGINATION-BASED AGENT NEURAL NETWORKS
- Publication number 20200082227
- Publication date Mar 12, 2020
- DeepMind Technologies Limited
- Daniel Pieter Wierstra
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS
- Publication number 20190354813
- Publication date Nov 21, 2019
- DeepMind Technologies Limited
- Martin Riedmiller
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING ACTION SELECTION NEURAL NETWORKS
- Publication number 20190258918
- Publication date Aug 22, 2019
- DeepMind Technologies Limited
- Ziyu Wang
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
NEURAL NETWORKS FOR SELECTING ACTIONS TO BE PERFORMED BY A ROBOTIC...
- Publication number 20190232489
- Publication date Aug 1, 2019
- DeepMind Technologies Limited
- Razvan Pascanu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
REINFORCEMENT AND IMITATION LEARNING FOR A TASK
- Publication number 20190126472
- Publication date May 2, 2019
- DeepMind Technologies Limited
- Saran Tunyasuvunakool
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING
- Publication number 20170024643
- Publication date Jan 26, 2017
- Google Inc.
- Timothy Paul Lillicrap
- G06 - COMPUTING CALCULATING COUNTING

Nicolas Manfred Otto Heess

Person

Patents Grantslast 30 patents

Training action selection neural networks using off-policy actor cr...

Multi-task neural network systems with task-specific policies and a...

Training action selection neural networks using apprenticeship

Selecting reinforcement learning actions using a low-level controller

Training action selection neural networks using apprenticeship

Continuous control with deep reinforcement learning

Data-efficient reinforcement learning for continuous control tasks

Neural networks for selecting actions to be performed by a robotic...

Training action selection neural networks using apprenticeship

Imagination-based agent neural networks

Selecting reinforcement learning actions using a low-level controller

Multi-task neural network systems with task-specific policies and a...

Imagination-based agent neural networks

Imagination-based agent neural networks

Continuous control with deep reinforcement learning

Training action selection neural networks using off-policy actor cr...

Data-efficient reinforcement learning for continuous control tasks

Neural networks for selecting actions to be performed by a robotic...

Patents Applicationslast 30 patents

NEURAL POPULATION LEARNING

HIERARCHICAL LATENT MIXTURE POLICIES FOR AGENT CONTROL

CONTROLLING AGENTS USING SUB-GOALS GENERATED BY LANGUAGE MODEL NEUR...

PLANNING USING A JUMPY TRAJECTORY DECODER NEURAL NETWORK

CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING

DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS

REINFORCEMENT AND IMITATION LEARNING FOR A TASK

TRAINING AN ACTION SELECTION SYSTEM USING RELATIVE ENTROPY Q-LEARNING

TRAINING ACTION SELECTION NEURAL NETWORKS USING APPRENTICESHIP

TRAINING ACTION SELECTION NEURAL NETWORKS USING HINDSIGHT MODELLING

NEURAL NETWORKS FOR SELECTING ACTIONS TO BE PERFORMED BY A ROBOTIC...

HIERARCHICAL POLICIES FOR MULTITASK TRANSFER

MULTI-TASK NEURAL NETWORK SYSTEMS WITH TASK-SPECIFIC POLICIES AND A...

IMAGINATION-BASED AGENT NEURAL NETWORKS

IMAGINATION-BASED AGENT NEURAL NETWORKS

GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS

CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING

TRAINING ACTION SELECTION NEURAL NETWORKS USING OFF-POLICY ACTOR CR...

DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS

NEURAL NETWORKS FOR SELECTING ACTIONS TO BE PERFORMED BY A ROBOTIC...

TRAINING ACTION SELECTION NEURAL NETWORKS USING APPRENTICESHIP

DATA EFFICIENT IMITATION OF DIVERSE BEHAVIORS

MULTI-TASK NEURAL NETWORK SYSTEMS WITH TASK-SPECIFIC POLICIES AND A...

IMAGINATION-BASED AGENT NEURAL NETWORKS

IMAGINATION-BASED AGENT NEURAL NETWORKS

DATA-EFFICIENT REINFORCEMENT LEARNING FOR CONTINUOUS CONTROL TASKS

TRAINING ACTION SELECTION NEURAL NETWORKS

NEURAL NETWORKS FOR SELECTING ACTIONS TO BE PERFORMED BY A ROBOTIC...

REINFORCEMENT AND IMITATION LEARNING FOR A TASK

CONTINUOUS CONTROL WITH DEEP REINFORCEMENT LEARNING