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 off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Abstract: An off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Abstract: A pressure sensor apparatus and a method of operating the pressure sensor apparatus can include a hybrid pressure switch having a single switching point, the hybrid pressure switch comprising: a mechanical pressure switch; and an electronic pressure sensor, wherein the hybrid pressure switch monitors a media pressure with the mechanical pressure switch providing a switching function and the electronic pressure sensor providing a continuous pressure measurement with respect to the media pressure based on a continuous pressure output signal. The switching function can comprise a fail-safe switching function or a non-fail-safe switching function.

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: A sensor system and method of operating the sensor system can include an indicator that is operable in resonance, the indicator being connected to a movable element of an actuator, and a sensor including sensor windings arranged in direct proximity to the indicator and external to a closed housing. The sensor can receive a position or an angle of the indicator, and can measure the position or the angle of the movable element inside the actuator through the closed housing based on inductive resonance facilitated by the indicator.

Abstract: An off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Abstract: An off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

Abstract: The present application relates to novel 3-phenylpropionic acid derivatives which carry a branched or cyclic alkyl substituent in the 3-position, to processes for their preparation, to their use for the treatment and/or prevention of diseases and to their use for preparing medicaments for the treatment and/or prevention of diseases, in particular for the treatment and/or prevention of cardiovascular diseases.

Abstract: A pressure sensor apparatus and a method of operating the pressure sensor apparatus can include a hybrid pressure switch having a single switching point, the hybrid pressure switch comprising: a mechanical pressure switch; and an electronic pressure sensor, wherein the hybrid pressure switch monitors a media pressure with the mechanical pressure switch providing a switching function and the electronic pressure sensor providing a continuous pressure measurement with respect to the media pressure based on a continuous pressure output signal. The switching function can comprise a fail-safe switching function or a non-fail-safe switching function.

Abstract: A sensor system and method of operating the sensor system can include an indicator that is operable in resonance, the indicator being connected to a movable element of an actuator, and a sensor including sensor windings arranged in direct proximity to the indicator and external to a closed housing. The sensor can receive a position or an angle of the indicator, and can measure the position or the angle of the movable element inside the actuator through the closed housing based on inductive resonance facilitated by the indicator.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a policy neural network for use in controlling a real-world agent in a real-world environment. One of the methods includes training the policy neural network by optimizing a first task-specific objective that measures a performance of the policy neural network in controlling a simulated version of the real-world agent; and then training the policy neural network by jointly optimizing (i) a self-supervised objective that measures at least a performance of internal representations generated by the policy neural network on a self-supervised task performed on real-world data and (ii) a second task-specific objective that measures the performance of the policy neural network in controlling the simulated version of the real-world agent.

Abstract: The present application relates to novel 3-phenylpropionic acid derivatives which carry a branched or cyclic alkyl substituent in the 3-position, to processes for their preparation, to their use for the treatment and/or prevention of diseases and to their use for preparing medicaments for the treatment and/or prevention of diseases, in particular for the treatment and/or prevention of cardiovascular diseases.

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 off-policy reinforcement learning actor-critic neural network system configured to select actions from a continuous action space to be performed by an agent interacting with an environment to perform a task. An observation defines environment state data and reward data. The system has an actor neural network which learns a policy function mapping the state data to action data. A critic neural network learns an action-value (Q) function. A replay buffer stores tuples of the state data, the action data, the reward data and new state data. The replay buffer also includes demonstration transition data comprising a set of the tuples from a demonstration of the task within the environment. The neural network system is configured to train the actor neural network and the critic neural network off-policy using stored tuples from the replay buffer comprising tuples both from operation of the system and from the demonstration transition data.

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: The present application relates to novel 3-phenylpropionic acid derivatives which carry a branched or cyclic alkyl substituent in the 3-position, to processes for their preparation, to their use for the treatment and/or prevention of diseases and to their use for preparing medicaments for the treatment and/or prevention of diseases, in particular for the treatment and/or prevention of cardiovascular diseases.

Abstract: The present application relates to novel 3-phenylpropionic acid derivatives which carry a branched or cyclic alkyl substituent in the 3-position, to processes for their preparation, to their use for the treatment and/or prevention of diseases and to their use for preparing medicaments for the treatment and/or prevention of diseases, in particular for the treatment and/or prevention of cardiovascular diseases.

Abstract: The invention relates to substituted dihydroquinazolines and to processes for their preparation and also to their use for preparing medicaments for the treatment and/or prophylaxis of diseases, in particular for use as antiviral agents, in particular against cytomegalo viruses.