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 a computer storage medium, for performing a machine learning task on a network input that is a sequence to generate a network output. In one aspect, one of the methods includes, for each particular sequence of layer inputs: for each attention layer in the neural network: maintaining episodic memory data; maintaining compressed memory data; receiving a layer input to be processed by the attention layer; and applying an attention mechanism over (i) the compressed representation in the compressed memory data for the layer, (ii) the hidden states in the episodic memory data for the layer, and (iii) the respective hidden state at each of the plurality of input positions in the particular network input to generate a respective activation for each input position in the layer input.

Abstract: Methods, systems, and apparatus for selecting actions to be performed by an agent interacting with an environment. One system includes a high-level controller neural network, low-level controller network, and subsystem. The high-level controller neural network receives an input observation and processes the input observation to generate a high-level output defining a control signal for the low-level controller. The low-level controller neural network receives a designated component of an input observation and processes the designated component and an input control signal to generate a low-level output that defines an action to be performed by the agent in response to the input observation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input that is a sequence to generate a network output. In one aspect, one of the methods includes, for each particular sequence of layer inputs: for each attention layer in the neural network: maintaining episodic memory data; maintaining compressed memory data; receiving a layer input to be processed by the attention layer; and applying an attention mechanism over (i) the compressed representation in the compressed memory data for the layer, (ii) the hidden states in the episodic memory data for the layer, and (iii) the respective hidden state at each of the plurality of input positions in the particular network input to generate a respective activation for each input position in the layer input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an actor neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining a minibatch of experience tuples; and updating current values of the parameters of the actor neural network, comprising: for each experience tuple in the minibatch: processing the training observation and the training action in the experience tuple using a critic neural network to determine a neural network output for the experience tuple, and determining a target neural network output for the experience tuple; updating current values of the parameters of the critic neural network using errors between the target neural network outputs and the neural network outputs; and updating the current values of the parameters of the actor neural network using the critic neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task. One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.

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 computer-implemented method for controlling a particular computer to execute a task is described. The method includes receiving a control input comprising a visual input, the visual input including one or more screen frames of a computer display that represent at least a current state of the particular computer; processing the control input using a neural network to generate one or more control outputs that are used to control the particular computer to execute the task, in which the one or more control outputs include an action type output that specifies at least one of a pointing device action or a keyboard action to be performed to control the particular computer; determining one or more actions from the one or more control outputs; and executing the one or more actions to control the particular computer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an interactive agent can be controlled based on multi-modal inputs that include both an observation image and a natural language text sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for computing Q values for actions to be performed by an agent interacting with an environment from a continuous action space of actions. In one aspect, a system includes a value subnetwork configured to receive an observation characterizing a current state of the environment and process the observation to generate a value estimate; a policy subnetwork configured to receive the observation and process the observation to generate an ideal point in the continuous action space; and a subsystem configured to receive a particular point in the continuous action space representing a particular action; generate an advantage estimate for the particular action; and generate a Q value for the particular action that is an estimate of an expected return resulting from the agent performing the particular action when the environment is in the current state.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing associative memory. In one aspect a system comprises an associative memory neural network to process an input to generate an output that defines an energy corresponding to the input. A reading subsystem retrieves stored information from the associative memory neural network. The reading subsystem performs operations including receiving a given, i.e. query, input and retrieving a data element from the associative memory neural network that is associated with the given input. The retrieving is performed by iteratively adjusting the given input using the associative memory neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for computing Q values for actions to be performed by an agent interacting with an environment from a continuous action space of actions. In one aspect, a system includes a value subnetwork configured to receive an observation characterizing a current state of the environment and process the observation to generate a value estimate; a policy subnetwork configured to receive the observation and process the observation to generate an ideal point in the continuous action space; and a subsystem configured to receive a particular point in the continuous action space representing a particular action; generate an advantage estimate for the particular action; and generate a Q value for the particular action that is an estimate of an expected return resulting from the agent performing the particular action when the environment is in the current state.

Abstract: Methods, systems, and apparatus for selecting actions to be performed by an agent interacting with an environment. One system includes a high-level controller neural network, low-level controller network, and subsystem. The high-level controller neural network receives an input observation and processes the input observation to generate a high-level output defining a control signal for the low-level controller. The low-level controller neural network receives a designated component of an input observation and processes the designated component and an input control signal to generate a low-level output that defines an action to be performed by the agent in response to the input observation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a sparse memory access subsystem that is configured to perform operations comprising generating a sparse set of reading weights that includes a respective reading weight for each of the plurality of locations in the external memory using the read key, reading data from the plurality of locations in the external memory in accordance with the sparse set of reading weights, generating a set of writing weights that includes a respective writing weight for each of the plurality of locations in the external memory, and writing the write vector to the plurality of locations in the external memory in accordance with the writing weights.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection policy neural network used to select an action to be performed by an agent interacting with an environment. In one aspect, a method includes: receiving a latent representation characterizing a current state of the environment; generating a trajectory of latent representations that starts with the received latent representation; for each latent representation in the trajectory: determining a predicted reward; and processing the state latent representation using a value neural network to generate a predicted state value; determining a corresponding target state value for each latent representation in the trajectory; determining, based on the target state values, an update to the current values of the policy neural network parameters; and determining an update to the current values of the value neural network parameters.

Abstract: A system for compressed data storage using a neural network. The system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input that is a sequence to generate a network output. In one aspect, one of the methods includes, for each particular sequence of layer inputs: for each attention layer in the neural network: maintaining episodic memory data; maintaining compressed memory data; receiving a layer input to be processed by the attention layer; and applying an attention mechanism over (i) the compressed representation in the compressed memory data for the layer, (ii) the hidden states in the episodic memory data for the layer, and (iii) the respective hidden state at each of the plurality of input positions in the particular network input to generate a respective activation for each input position in the layer input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network system used to control an agent interacting with an environment to perform a specified task. One of the methods includes causing the agent to perform a task episode in which the agent attempts to perform the specified task; for each of one or more particular time steps in the sequence: generating a modified reward for the particular time step from (i) the actual reward at the time step and (ii) value predictions at one or more time steps that are more than a threshold number of time steps after the particular time step in the sequence; and training, through reinforcement learning, the neural network system using at least the modified rewards for the particular time steps.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a memory-based prediction system configured to receive an input observation characterizing a state of an environment interacted with by an agent and to process the input observation and data read from a memory to update data stored in the memory and to generate a latent representation of the state of the environment. The method comprises: for each of a plurality of time steps: processing an observation for the time step and data read from the memory to: (i) update the data stored in the memory, and (ii) generate a latent representation of the current state of the environment as of the time step; and generating a predicted return that will be received by the agent as a result of interactions with the environment after the observation for the time step is received.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a controller neural network that includes a Least Recently Used Access (LRUA) subsystem configured to: maintain a respective usage weight for each of a plurality of locations in the external memory, and for each of the plurality of time steps: generate a respective reading weight for each location using a read key, read data from the locations in accordance with the reading weights, generate a respective writing weight for each of the locations from a respective reading weight from a preceding time step and the respective usage weight for the location, write a write vector to the locations in accordance with the writing weights, and update the respective usage weight from the respective reading weight and the respective writing weight.