Noisy neural network layers with noise parameters

    公开(公告)号:US11977983B2

    公开(公告)日:2024-05-07

    申请号:US17020248

    申请日:2020-09-14

    CPC classification number: G06N3/084 G06N3/044

    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. The method includes obtaining an observation characterizing a current state of an environment. For each layer parameter of each noisy layer of a neural network, a respective noise value is determined. For each layer parameter of each noisy layer, a noisy current value for the layer parameter is determined from a current value of the layer parameter, a current value of a corresponding noise parameter, and the noise value. A network input including the observation is processed using the neural network in accordance with the noisy current values to generate a network output for the network input. An action is selected from a set of possible actions to be performed by the agent in response to the observation using the network output.

    LEARNING ENVIRONMENT REPRESENTATIONS FOR AGENT CONTROL USING PREDICTIONS OF BOOTSTRAPPED LATENTS

    公开(公告)号:US20230083486A1

    公开(公告)日:2023-03-16

    申请号:US17797886

    申请日:2021-02-08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an environment representation neural network of a reinforcement learning system controls an agent to perform a given task. In one aspect, the method includes: receiving a current observation input and a future observation input; generating, from the future observation input, a future latent representation of the future state of the environment; processing, using the environment representation neural network, to generate a current internal representation of the current state of the environment; generating, from the current internal representation, a predicted future latent representation; evaluating an objective function measuring a difference between the future latent representation and the predicted future latent representation; and determining, based on a determined gradient of the objective function, an update to the current values of the environment representation parameters.

    NOISY NEURAL NETWORK LAYERS WITH NOISE PARAMETERS

    公开(公告)号:US20210065012A1

    公开(公告)日:2021-03-04

    申请号:US17020248

    申请日:2020-09-14

    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. The method includes obtaining an observation characterizing a current state of an environment. For each layer parameter of each noisy layer of a neural network, a respective noise value is determined. For each layer parameter of each noisy layer, a noisy current value for the layer parameter is determined from a current value of the layer parameter, a current value of a corresponding noise parameter, and the noise value. A network input including the observation is processed using the neural network in accordance with the noisy current values to generate a network output for the network input. An action is selected from a set of possible actions to be performed by the agent in response to the observation using the network output.

    Training action selection neural networks using leave-one-out-updates

    公开(公告)号:US11604997B2

    公开(公告)日:2023-03-14

    申请号:US16603307

    申请日:2018-06-11

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network. The policy neural network is used to select actions to be performed by an agent that interacts with an environment by receiving an observation characterizing a state of the environment and performing an action from a set of actions in response to the received observation. A trajectory is obtained from a replay memory, and a final update to current values of the policy network parameters is determined for each training observation in the trajectory. The final updates to the current values of the policy network parameters are determined from selected action updates and leave-one-out updates.

    TRAINING ACTION SELECTION NEURAL NETWORKS

    公开(公告)号:US20210110271A1

    公开(公告)日:2021-04-15

    申请号:US16603307

    申请日:2018-06-11

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a policy neural network. The policy neural network is used to select actions to be performed by an agent that interacts with an environment by receiving an observation characterizing a state of the environment and performing an action from a set of actions in response to the received observation. A trajectory is obtained from a replay memory, and a final update to current values of the policy network parameters is determined for each training observation in the trajectory. The final updates to the current values of the policy network parameters are determined from selected action updates and leave-one-out updates.

Patent Agency Ranking