Hado Philip van Hasselt

Person

London, GB

People

Patents Grantslast 30 patents

Information Patent Grant
Continual reinforcement learning with a multi-task agent
- Patent number 12,154,029
- Issue date Nov 26, 2024
- DeepMind Technologies Limited
- Tom Schaul
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Environment prediction using reinforcement learning
- Patent number 12,141,677
- Issue date Nov 12, 2024
- DeepMind Technologies Limited
- David Silver
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training reinforcement learning neural networks
- Patent number 11,886,992
- Issue date Jan 30, 2024
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Meta-gradient updates for training return functions for reinforceme...
- Patent number 11,836,620
- Issue date Dec 5, 2023
- DeepMind Technologies Limited
- Zhongwen Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training neural networks using normalized target outputs
- Patent number 11,769,051
- Issue date Sep 26, 2023
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training action selection neural networks using a differentiable cr...
- Patent number 11,651,208
- Issue date May 16, 2023
- DeepMind Technologies Limited
- Zhongwen Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training neural networks using normalized target outputs
- Patent number 11,062,206
- Issue date Jul 13, 2021
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Meta-gradient updates for training return functions for reinforceme...
- Patent number 10,860,926
- Issue date Dec 8, 2020
- DeepMind Technologies Limited
- Zhongwen Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Environment prediction using reinforcement learning
- Patent number 10,733,501
- Issue date Aug 4, 2020
- DeepMind Technologies Limited
- David Silver
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training reinforcement learning neural networks
- Patent number 10,733,504
- Issue date Aug 4, 2020
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING

Patents Applicationslast 30 patents

Information Patent Application
GENERATING ENVIRONMENT MODELS USING IN-CONTEXT ADAPTATION AND EXPLO...
- Publication number 20240256884
- Publication date Aug 1, 2024
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
REINFORCEMENT LEARNING USING EPISTEMIC VALUE ESTIMATION
- Publication number 20240232642
- Publication date Jul 11, 2024
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
LEARNING OPTIONS FOR ACTION SELECTION WITH META-GRADIENTS IN MULTI-...
- Publication number 20230144995
- Publication date May 11, 2023
- DeepMind Technologies Limited
- Vivek Veeriah Jeya Veeraiah
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING NEURAL NETWORKS USING NORMALIZED TARGET OUTPUTS
- Publication number 20210319316
- Publication date Oct 14, 2021
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
META-GRADIENT UPDATES FOR TRAINING RETURN FUNCTIONS FOR REINFORCEME...
- Publication number 20210089915
- Publication date Mar 25, 2021
- DeepMind Technologies Limited
- Zhongwen Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING REINFORCEMENT LEARNING NEURAL NETWORKS
- Publication number 20200364569
- Publication date Nov 19, 2020
- DeepMind Technologies Limited
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
ENVIRONMENT PREDICTION USING REINFORCEMENT LEARNING
- Publication number 20200327399
- Publication date Oct 15, 2020
- DeepMind Technologies Limited
- David Silver
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING ACTION SELECTION NEURAL NETWORKS USING A DIFFERENTIABLE CR...
- Publication number 20200175364
- Publication date Jun 4, 2020
- Zhongwen Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
META-GRADIENT UPDATES FOR TRAINING RETURN FUNCTIONS FOR REINFORCEME...
- Publication number 20190354859
- Publication date Nov 21, 2019
- DeepMind Technologies Limited
- Zhongwen Xu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
ENVIRONMENT PREDICTION USING REINFORCEMENT LEARNING
- Publication number 20190259051
- Publication date Aug 22, 2019
- DeepMind Technologies Limited
- David Silver
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
CONTINUAL REINFORCEMENT LEARNING WITH A MULTI-TASK AGENT
- Publication number 20190244099
- Publication date Aug 8, 2019
- DeepMind Technologies Limited
- Tom Schaul
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING NEURAL NETWORKS USING NORMALIZED TARGET OUTPUTS
- Publication number 20170140268
- Publication date May 18, 2017
- Google Inc.
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
TRAINING REINFORCEMENT LEARNING NEURAL NETWORKS
- Publication number 20170076201
- Publication date Mar 16, 2017
- Google Inc.
- Hado Philip van Hasselt
- G06 - COMPUTING CALCULATING COUNTING

Hado Philip van Hasselt

Person

Patents Grantslast 30 patents

Continual reinforcement learning with a multi-task agent

Environment prediction using reinforcement learning

Training reinforcement learning neural networks

Meta-gradient updates for training return functions for reinforceme...

Training neural networks using normalized target outputs

Training action selection neural networks using a differentiable cr...

Training neural networks using normalized target outputs

Meta-gradient updates for training return functions for reinforceme...

Environment prediction using reinforcement learning

Training reinforcement learning neural networks

Patents Applicationslast 30 patents

GENERATING ENVIRONMENT MODELS USING IN-CONTEXT ADAPTATION AND EXPLO...

REINFORCEMENT LEARNING USING EPISTEMIC VALUE ESTIMATION

LEARNING OPTIONS FOR ACTION SELECTION WITH META-GRADIENTS IN MULTI-...

TRAINING NEURAL NETWORKS USING NORMALIZED TARGET OUTPUTS

META-GRADIENT UPDATES FOR TRAINING RETURN FUNCTIONS FOR REINFORCEME...

TRAINING REINFORCEMENT LEARNING NEURAL NETWORKS

ENVIRONMENT PREDICTION USING REINFORCEMENT LEARNING

TRAINING ACTION SELECTION NEURAL NETWORKS USING A DIFFERENTIABLE CR...

META-GRADIENT UPDATES FOR TRAINING RETURN FUNCTIONS FOR REINFORCEME...

ENVIRONMENT PREDICTION USING REINFORCEMENT LEARNING

CONTINUAL REINFORCEMENT LEARNING WITH A MULTI-TASK AGENT

TRAINING NEURAL NETWORKS USING NORMALIZED TARGET OUTPUTS

TRAINING REINFORCEMENT LEARNING NEURAL NETWORKS