DeepMind Technologies Limited patent applications on April 10th, 2025
Patent Applications by DeepMind Technologies Limited on April 10th, 2025
DeepMind Technologies Limited: 2 patent applications
DeepMind Technologies Limited has applied for patents in the areas of G06N3/08 (2), G06F18/2113 (1), G06N3/045 (1), G06N3/063 (1), H03K19/173 (1) G06N3/08 (2)
With keywords such as: value, output, values, probability, action, observation, current, computer, distribution, and recurrent in patent application abstracts.
Patent Applications by DeepMind Technologies Limited
Inventor(s): Nal Emmerich Kalchbrenner of Amsterdam NL for deepmind technologies limited, Karen Simonyan of London GB for deepmind technologies limited, Erich Konrad Elsen of Naperville IL US for deepmind technologies limited
IPC Code(s): G06N3/08, G06F18/2113, G06N3/045, G06N3/063, H03K19/173
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. each output example includes multiple n-bit output values. to generate a given n-bit output value, a first recurrent input comprising the preceding n-bit output value is processed using a recurrent neural network and in accordance with a hidden state to generate a first score distribution. then, values for the first half of the n bits are selected. a second recurrent input comprising (i) the preceding n-bit output value and (ii) the values for the first half of the n bits are processed using the recurrent neural network and in accordance with the same hidden state to generate a second score distribution. the values for the second half of the n bits of the output value are then selected using the second score distribution.
Inventor(s): Georg Ostrovski of London GB for deepmind technologies limited, William Clinton Dabney of London GB for deepmind technologies limited
IPC Code(s): G06N3/08, G06N3/04
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an action to be performed by a reinforcement learning agent interacting with an environment. in one aspect, a method comprises: receiving a current observation; for each action of a plurality of actions: randomly sampling one or more probability values; for each probability value: processing the action, the current observation, and the probability value using a quantile function network to generate an estimated quantile value for the probability value with respect to a probability distribution over possible returns that would result from the agent performing the action in response to the current observation; determining a measure of central tendency of the one or more estimated quantile values; and selecting an action to be performed by the agent in response to the current observation using the measures of central tendency for the actions.
DeepMind Technologies Limited patent applications on April 10th, 2025