Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning with scheduled auxiliary tasks. In one aspect, a method includes maintaining data specifying parameter values for a primary policy neural network and one or more auxiliary neural networks; at each of a plurality of selection time steps during a training episode comprising a plurality of time steps: receiving an observation, selecting a current task for the selection time step using a task scheduling policy, processing an input comprising the observation using the policy neural network corresponding to the selected current task to select an action to be performed by the agent in response to the observation, and causing the agent to perform the selected action.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes obtaining an observation characterizing a current state of the environment and data identifying a task currently being performed by the agent; processing the observation and the data identifying the task using a high-level controller to generate a high-level probability distribution that assigns a respective probability to each of a plurality of low-level controllers; processing the observation using each of the plurality of low-level controllers to generate, for each of the plurality of low-level controllers, a respective low-level probability distribution; generating a combined probability distribution; and selecting, using the combined probability distribution, an action from the space of possible actions to be performed by the agent in response to the observation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-efficient reinforcement learning. One of the systems is a system for training an actor neural network used to select actions to be performed by an agent that interacts with an environment by receiving observations characterizing states of the environment and, in response to each observation, performing an action selected from a continuous space of possible actions, wherein the actor neural network maps observations to next actions in accordance with values of parameters of the actor neural network, and wherein the system comprises: a plurality of workers, wherein each worker is configured to operate independently of each other worker, wherein each worker is associated with a respective agent replica that interacts with a respective replica of the environment during the training of the actor neural network.

Abstract: An explosion-proof sliding gate valve (1) for blocking a fluid flow (F) in a pipeline, which comprises: a sliding gate valve housing (2), a sealing plate (3) which is movably mounted in the slide gate valve housing (2) between an operating position (B) and a closed position (S), wherein in the closed position (S) the sealing plate (3) blocks the fluid flow (F), a mechanism for moving the sealing plate (3) from the operating position (B) into the closed position (S), and at least one deformation body (4) for damping movement of the sealing plate. The deformation body is arranged, according to the invention, at the side between sliding gate valve housing (2) and sealing plate (3).

Abstract: An explosion-proof sliding gate valve (1) for blocking a fluid flow (F) in a pipeline, which comprises: a sliding gate valve housing (2), a sealing plate (3) which is movably mounted in the slide gate valve housing (2) between an operating position (B) and a closed position (S), wherein in the closed position (S) the sealing plate (3) blocks the fluid flow (F), a mechanism for moving the sealing plate (3) from the operating position (B) into the closed position (S), and at least one deformation body (4) for damping movement of the sealing plate. The deformation body is arranged, according to the invention, at the side between sliding gate valve housing (2) and sealing plate (3).

Abstract: In a method for determining a rail pressure setpoint value for a high-pressure rail of an internal combustion engine, the rail pressure setpoint value is modified to a maximum degree using a maximum gradient for changing the rail pressure setpoint value, and the maximum gradient is read from a characteristics map as a function of operating parameters of the internal combustion engine. The operating parameters include an engaged gear of a gear-change transmission.

Abstract: In a method for determining a rail pressure setpoint value for a high-pressure rail of an internal combustion engine, the rail pressure setpoint value is modified to a maximum degree using a maximum gradient for changing the rail pressure setpoint value, and the maximum gradient is read from a characteristics map as a function of operating parameters of the internal combustion engine. The operating parameters include an engaged gear of a gear-change transmission.