专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2022167600A1 TEMPORAL DIFFERENCE SCALING WHEN CONTROLLING AGENTS USING REINFORCEMENT LEARNING 审中-公开
公开(公告)号：WO2022167600A1
公开(公告)日：2022-08-11
申请号：PCT/EP2022/052751
申请日：2022-02-04
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： SCHAUL, Tom
IPC分类号： G06N3/04 , G06N3/08 , G06N3/00
摘要： A reinforcement learning neural network system configured to manage rewards on scales that can vary significantly. The system determines the value of a scale factor that is applied to a temporal difference error used for reinforcement learning. The scale factor depends at least upon a variance of the rewards received during the reinforcement learning.

2. 发明申请

WO2018083667A1 REINFORCEMENT LEARNING SYSTEMS 审中-公开
标题翻译：加强学习系统
公开(公告)号：WO2018083667A1
公开(公告)日：2018-05-11
申请号：PCT/IB2017/056902
申请日：2017-11-04
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： SILVER, David , SCHAUL, Tom , HESSEL, Matteo , VAN HASSELT, Hado Philip
IPC分类号： G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for prediction of an outcome related to an environment. In one aspect, a system comprises a state representation neural network that is configured to: receive an observation characterizing a state of an environment being interacted with by an agent and process the observation to generate an internal state representation of the environment state; a prediction neural network that is configured to receive a current internal state representation of a current environment state and process the current internal state representation to generate a predicted subsequent state representation of a subsequent state of the environment and a predicted reward for the subsequent state; and a value prediction neural network that is configured to receive a current internal state representation of a current environment state and process the current internal state representation to generate a value prediction.
摘要翻译：包括编码在计算机存储介质上的计算机程序的方法，系统和装置用于预测与环境有关的结果。在一个方面中，一种系统包括状态表示神经网络，所述状态表示神经网络被配置为：接收表征代理与之交互的环境的状态的观察结果，并处理所述观察结果以生成所述环境状态的内部状态表示; 预测神经网络，其被配置为接收当前环境状态的当前内部状态表示并且处理所述当前内部状态表示以生成所述环境的后续状态的预测后续状态表示和所述后续状态的预测奖励; 以及值预测神经网络，其被配置为接收当前环境状态的当前内部状态表示并且处理当前内部状态表示以生成值预测。

3. 发明申请

WO2023012234A1 CONTROLLING AGENTS BY SWITCHING BETWEEN CONTROL POLICIES DURING TASK EPISODES 审中-公开
公开(公告)号：WO2023012234A1
公开(公告)日：2023-02-09
申请号：PCT/EP2022/071864
申请日：2022-08-03
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： SCHAUL, Tom , PÎSLAR, Miruna
IPC分类号： G06N3/04 , G06N3/08 , G06N3/00
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an agent can be controlled to perform a task episode by switching the control policy that is used to control the agent at one or more time steps during the task episode.

4. 发明申请

WO2020152267A1 LEARNING NON-DIFFERENTIABLE WEIGHTS OF NEURAL NETWORKS USING EVOLUTIONARY STRATEGIES 审中-公开
公开(公告)号：WO2020152267A1
公开(公告)日：2020-07-30
申请号：PCT/EP2020/051623
申请日：2020-01-23
申请人： DEEPMIND TECHNOLOGIES LIMITED , SCHAUL, Tom , ELSEN, Erich Konrad
发明人： SCHAUL, Tom , ELSEN, Erich Konrad , LENC, Karel , SIMONYAN, Karen
IPC分类号： G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. The neural network has a plurality of differentiable weights and a plurality of non-differentiable weights. One of the methods includes determining trained values of the plurality of differentiable weights and the non-differentiable weights by repeatedly performing operations that include determining an update to the current values of the plurality of differentiable weights using a machine learning gradient-based training technique and determining, using an evolution strategies (ES) technique, an update to the current values of a plurality of distribution parameters.

5. 发明申请

WO2018083671A1 REINFORCEMENT LEARNING WITH AUXILIARY TASKS 审中-公开
标题翻译：辅助任务加强学习
公开(公告)号：WO2018083671A1
公开(公告)日：2018-05-11
申请号：PCT/IB2017/056906
申请日：2017-11-04
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： MNIH, Volodymyr , CZARNECKI, Wojciech , JADERBERG, Maxwell Elliot , SCHAUL, Tom , SILVER, David , KAVUKCUOGLU, Koray
IPC分类号： G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. The method includes: training an action selection policy neural network, and during the training of the action selection neural network, training one or more auxiliary control neural networks and a reward prediction neural network. Each of the auxiliary control neural networks is configured to receive a respective intermediate output generated by the action selection policy neural network and generate a policy output for a corresponding auxiliary control task. The reward prediction neural network is configured to receive one or more intermediate outputs generated by the action selection policy neural network and generate a corresponding predicted reward. Training each of the auxiliary control neural networks and the reward prediction neural network comprises adjusting values of the respective auxiliary control parameters, reward prediction parameters, and the action selection policy network parameters.
摘要翻译：包括编码在计算机存储介质上的用于训练强化学习系统的计算机程序的方法，系统和装置。该方法包括：训练动作选择策略神经网络，并且在训练动作选择神经网络期间，训练一个或多个辅助控制神经网络和奖励预测神经网络。每个辅助控制神经网络被配置为接收由动作选择策略神经网络生成的相应中间输出并且为相应的辅助控制任务生成策略输出。奖励预测神经网络被配置为接收由动作选择策略神经网络生成的一个或多个中间输出并且生成对应的预测奖励。训练每个辅助控制神经网络和奖励预测神经网络包括调整各个辅助控制参数，奖励预测参数和动作选择策略网络参数的值。

6. 发明公开

EP3535705A1 REINFORCEMENT LEARNING WITH AUXILIARY TASKS 有权转让
公开(公告)号：EP3535705A1
公开(公告)日：2019-09-11
申请号：EP17808163.4
申请日：2017-11-04
申请人： Deepmind Technologies Limited
发明人： MNIH, Volodymyr , CZARNECKI, Wojciech , JADERBERG, Maxwell Elliot , SCHAUL, Tom , SILVER, David , KAVUKCUOGLU, Koray
IPC分类号： G06N3/04 , G06N3/08

7. 发明公开

EP4356302A1 CONTROLLING AGENTS BY SWITCHING BETWEEN CONTROL POLICIES DURING TASK EPISODES 审中-实审
公开(公告)号：EP4356302A1
公开(公告)日：2024-04-24
申请号：EP22761485.6
申请日：2022-08-03
申请人： DeepMind Technologies Limited
发明人： SCHAUL, Tom , PÎSLAR, Miruna
IPC分类号： G06N3/04 , G06N3/08 , G06N3/00
CPC分类号： G06N3/006 , G06N3/045 , G06N3/092 , G06N3/0464

8. 发明公开

EP4268134A1 TEMPORAL DIFFERENCE SCALING WHEN CONTROLLING AGENTS USING REINFORCEMENT LEARNING 审中-实审
公开(公告)号：EP4268134A1
公开(公告)日：2023-11-01
申请号：EP22707376.4
申请日：2022-02-04
申请人： DeepMind Technologies Limited
发明人： SCHAUL, Tom
IPC分类号： G06N3/04 , G06N3/08 , G06N3/00

9. 发明公开

EP3915059A1 LEARNING NON-DIFFERENTIABLE WEIGHTS OF NEURAL NETWORKS USING EVOLUTIONARY STRATEGIES 审中-实审
公开(公告)号：EP3915059A1
公开(公告)日：2021-12-01
申请号：EP20701748.4
申请日：2020-01-23
申请人： DeepMind Technologies Limited
发明人： SCHAUL, Tom , ELSEN, Erich Konrad , LENC, Karel , SIMONYAN, Karen
IPC分类号： G06N3/08

10. 发明公开

EP3523760A1 REINFORCEMENT LEARNING SYSTEMS 有权转让
公开(公告)号：EP3523760A1
公开(公告)日：2019-08-14
申请号：EP17807934.9
申请日：2017-11-04
申请人： Deepmind Technologies Limited
发明人： SILVER, David , SCHAUL, Tom , HESSEL, Matteo , VAN HASSELT, Hado Philip
IPC分类号： G06N3/04 , G06N3/08

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式