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.

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.

Abstract: A tube fitting for connection to a tube includes a main body structure and a tube liner. The main body structure is configured to receive an end of the tube and fluidly connect the tube to another component. The tube liner is positioned at least partially within the main body structure and is configured to extend into the tube. The main body structure and the tube liner are configured such that, when the tube is fully inserted into the tube fitting, the end of the tube is positioned at a predetermined depth within the tube fitting, and the main body structure and the tube liner cooperate together to provide an audible indication to indicate that the tube has been fully inserted into the tube fitting.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing and storing inputs for use in a neural network. One of the methods includes receiving input data for storage in a memory system comprising a first set of memory blocks, the memory blocks having an associated order; passing the input data to a highest ordered memory block; for each memory block for which there is a lower ordered memory block: applying a filter function to data currently stored by the memory block to generate filtered data and passing the filtered data to a lower ordered memory block; and for each memory block: combining the data currently stored in the memory block with the data passed to the memory block to generate updated data, and storing the updated data in the memory block.

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.

Abstract: Disclosed is a semiconductor device such as a power amplifier. Unlike conventional power amplifiers, thermal bump is patterned to only cover active devices. In this way, dimensions of the semiconductor device can be reduced.

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.

Abstract: Disclosed is a semiconductor device such as a power amplifier. Unlike conventional power amplifiers, thermal bump is patterned to only cover active devices. In this way, dimensions of the semiconductor device can be reduced.

Abstract: A tube fitting for connection to a tube includes a main body structure and a tube liner. The main body structure is configured to receive an end of the tube and fluidly connect the tube to another component. The tube liner is positioned at least partially within the main body structure and is configured to extend into the tube. The main body structure and the tube liner are configured such that, when the tube is fully inserted into the tube fitting, the end of the tube is positioned at a predetermined depth within the tube fitting, and the main body structure and the tube liner cooperate together to provide an audible indication to indicate that the tube has been fully inserted into the tube fitting.

Abstract: A flexible heater connector can include a hose, a nut having a female tapered thread, and a fitting structure. The female tapered thread of the nut can engage a male tapered thread associated with the heater. The fitting structure can include a first portion to mechanically engage an inner wall of the hose, and a second portion mechanically coupled to the nut. The nut can be a swivel nut.

Abstract: A tube fitting for connection to a tube includes a main body structure and a tube liner. The main body structure is configured to receive an end of the tube and fluidly connect the tube to another component. The tube liner is positioned at least partially within the main body structure and is configured to extend into the tube. The main body structure and the tube liner are configured such that, when the tube is fully inserted into the tube fitting, the end of the tube is positioned at a predetermined depth within the tube fitting, and the main body structure and the tube liner cooperate together to provide an audible indication to indicate that the tube has been fully inserted into the tube fitting.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes sampling a behavior modulation in accordance with a current probability distribution; for each of one or more time steps: processing an input comprising an observation characterizing a current state of the environment at the time step using an action selection neural network to generate a respective action score for each action in a set of possible actions that can be performed by the agent; modifying the action scores using the sampled behavior modulation; and selecting the action to be performed by the agent at the time step based on the modified action scores; determining a fitness measure corresponding to the sampled behavior modulation; and updating the current probability distribution over the set of possible behavior modulations using the fitness measure corresponding to the behavior modulation.

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. A current observation characterizing a current state of the environment is received. For each action in a set of multiple actions that can be performed by the agent to interact with the environment, a probability distribution is determined over possible Q returns for the action-current observation pair. For each action, a measure of central tendency of the possible Q returns with respect to the probability distributions for the action-current observation pair is determined. An action to be performed by the agent in response to the current observation is selected using the measures of central tendency.

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. A current observation characterizing a current state of the environment is received. For each action in a set of multiple actions that can be performed by the agent to interact with the environment, a probability distribution is determined over possible Q returns for the action-current observation pair. For each action, a measure of central tendency of the possible Q returns with respect to the probability distributions for the action-current observation pair is determined. An action to be performed by the agent in response to the current observation is selected using the measures of central tendency.

Abstract: A wafer carrier comprising a board, a frame and at least one bolt and nut combination. The board includes at least one vacuum cavity and at least one securing cavity. The frame is coupled to the board. The at least one bolt and nut combination is configured to secure the frame to the board. The board may include one or more metal layers. The frame may include a plurality of scattered frames or a disc shaped frame. The frame may comprise a cavity for the bolt travels through the frame. The wafer carrier may include a wafer located over the board, wherein the wafer is located between the board and the frame.

Abstract: A flexible heater connector can include a hose, a nut having a female tapered thread, and a fitting structure. The female tapered thread of the nut can engage a male tapered thread associated with the heater. The fitting structure can include a first portion to mechanically engage an inner wall of the hose, and a second portion mechanically coupled to the nut. The nut can be a swivel nut.

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.

Abstract: A voice user interface (VUI) system use collaborative filtering to expand its own knowledge base. The system is designed to improve the accuracy and performance of the Natural Language Understanding (NLU) processing that underlies VUIs. The system leverages the knowledge of system users to crowdsource new information.

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. A current observation characterizing a current state of the environment is received. For each action in a set of multiple actions that can be performed by the agent to interact with the environment, a probability distribution is determined over possible Q returns for the action-current observation pair. For each action, a measure of central tendency of the possible Q returns with respect to the probability distributions for the action-current observation pair is determined. An action to be performed by the agent in response to the current observation is selected using the measures of central tendency.