Abstract: A method for invoking a user-intended Internet of Things (IoT) device amongst a number of IoT devices is disclosed. The method includes extracting by the number of IoT devices, a number of voice parameters from a voice wakeup command for waking up the device. The method includes sharing by the number of IoT devices, the number of voice parameters amongst the number of IoT devices. The method includes comparing the number of voice parameters with a number of pre-stored voice parameters in the number of IoT devices. The method includes determining, a user-intended IoT device amongst the number of IoT devices based on the voice wakeup command and at least one of a similarity between the plurality of pre-stored voice parameters and the plurality of voice parameters and a previously invoked IoT device associated with a previous voice wakeup command. The method includes invoking the user-intended IoT device selected amongst the number of IoT devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent interacting with an environment. One of the methods includes obtaining a representation of an observation; processing the representation using a convolutional long short-term memory (LSTM) neural network comprising a plurality of convolutional LSTM neural network layers; processing an action selection input comprising the final LSTM hidden state output for the time step using an action selection neural network that is configured to receive the action selection input and to process the action selection input to generate an action selection output that defines an action to be performed by the agent at the time step; selecting, from the action selection output, the action to be performed by the agent at the time step in accordance with an action selection policy; and causing the agent to perform the selected action.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent interacting with an environment. One of the methods includes obtaining a representation of an observation; processing the representation using a convolutional long short-term memory (LSTM) neural network comprising a plurality of convolutional LSTM neural network layers; processing an action selection input comprising the final LSTM hidden state output for the time step using an action selection neural network that is configured to receive the action selection input and to process the action selection input to generate an action selection output that defines an action to be performed by the agent at the time step; selecting, from the action selection output, the action to be performed by the agent at the time step in accordance with an action selection policy; and causing the agent to perform the selected action.