-
公开(公告)号:EP4386624A3
公开(公告)日:2024-08-07
申请号:EP24173836.8
申请日:2017-11-04
发明人: VIOLA, Fabio , MIROWSKI, Piotr Wojciech , BANINO, Andrea , PASCANU, Razvan , SOYER, Hubert Josef , BALLARD, Andrew James , KUMARAN, Sudarshan , HADSELL, Raia Thais , SIFRE, Laurent , GOROSHIN, Rostislav , KAVUKCUOGLU, Koray , DENIL, Misha Man Ray
IPC分类号: G06N3/006 , G06N3/0442 , G06N3/045 , G06N3/0464 , G06N3/084 , G06N3/092
CPC分类号: G06N3/084 , G06N3/006 , G06N3/045 , G06N3/0464 , G06N3/0442 , G06N3/092
摘要: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a loop closure prediction neural network, an intermediate output generated by the action selection policy neural network to predict whether the agent has returned to a location in the environment that the agent has already visited; and backpropagating a gradient of a loop closure based auxiliary loss into the action selection policy neural network to determine a loop closure based auxiliary update for current values of the network parameters.
-
2.
公开(公告)号:EP3782080A1
公开(公告)日:2021-02-24
申请号:EP19719243.8
申请日:2019-04-18
-
公开(公告)号:EP3602412A1
公开(公告)日:2020-02-05
申请号:EP18726143.3
申请日:2018-05-22
-
公开(公告)号:EP4446947A2
公开(公告)日:2024-10-16
申请号:EP24196237.2
申请日:2019-05-09
IPC分类号: G06N3/092
摘要: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a grid cell neural network and an action selection neural network. The grid cell network is configured to: receive an input comprising data characterizing a velocity of the agent; process the input to generate a grid cell representation; and process the grid cell representation to generate an estimate of a position of the agent in the environment; the action selection neural network is configured to: receive an input comprising a grid cell representation and an observation characterizing a state of the environment; and process the input to generate an action selection network output.
-
公开(公告)号:EP3523762A1
公开(公告)日:2019-08-14
申请号:EP17812054.9
申请日:2017-11-04
-
公开(公告)号:EP4386624A2
公开(公告)日:2024-06-19
申请号:EP24173836.8
申请日:2017-11-04
发明人: VIOLA, Fabio , MIROWSKI, Piotr Wojciech , BANINO, Andrea , PASCANU, Razvan , SOYER, Hubert Josef , BALLARD, Andrew James , KUMARAN, Sudarshan , HADSELL, Raia Thais , SIFRE, Laurent , GOROSHIN, Rostislav , KAVUKCUOGLU, Koray , DENIL, Misha Man Ray
IPC分类号: G06N3/045
CPC分类号: G06N3/084 , G06N3/006 , G06N3/045 , G06N3/0464 , G06N3/0442 , G06N3/092
摘要: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a loop closure prediction neural network, an intermediate output generated by the action selection policy neural network to predict whether the agent has returned to a location in the environment that the agent has already visited; and backpropagating a gradient of a loop closure based auxiliary loss into the action selection policy neural network to determine a loop closure based auxiliary update for current values of the network parameters.
-
公开(公告)号:EP3743853A1
公开(公告)日:2020-12-02
申请号:EP19723384.4
申请日:2019-05-09
-
公开(公告)号:EP3523758A1
公开(公告)日:2019-08-14
申请号:EP17788409.5
申请日:2017-10-10
-
公开(公告)号:EP4384952A1
公开(公告)日:2024-06-19
申请号:EP22800199.6
申请日:2022-10-05
发明人: RAO, Dushyant , SADEGHI, Fereshteh , HASENCLEVER, Leonard , WULFMEIER, Markus , ZAMBELLI, Martina , VEZZANI, Giulia , TIRUMALA BUKKAPATNAM, Dhruva , AYTAR, Yusuf , MEREL, Joshua , HEESS, Nicolas Manfred Otto , HADSELL, Raia Thais
IPC分类号: G06N3/092 , G06N3/0464 , G06N3/096 , G06N3/006 , G06N3/045
CPC分类号: G06N3/092 , G06N3/0464 , G06N3/096 , G06N3/006 , G06N3/045
-
公开(公告)号:EP4312157A3
公开(公告)日:2024-03-20
申请号:EP23199207.4
申请日:2016-12-30
发明人: RABINOWITZ, Neil Charles , DESJARDINS, Guillaume , RUSU, Andrei-Alexandru , KAVUKCUOGLU, Koray , HADSELL, Raia Thais , PASCANU, Razvan , KIRKPATRICK, James , SOYER, Hubert Josef
IPC分类号: G06N3/04
摘要: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.
-
-
-
-
-
-
-
-
-