GENERATIVE NEURAL NETWORK SYSTEMS FOR GENERATING INSTRUCTION SEQUENCES TO CONTROL AN AGENT PERFORMING A TASK

摘要

A generative adversarial neural network system to provide a sequence of actions for performing a task. The system comprises a reinforcement learning neural network subsystem coupled to a simulator and a discriminator neural network. The reinforcement learning neural network subsystem includes a policy recurrent neural network to, at each of a sequence of time steps, select one or more actions to be performed according to an action selection policy, each action comprising one or more control commands for a simulator. The simulator is configured to implement the control commands for the time steps to generate a simulator output. The discriminator neural network is configured to discriminate between the simulator output and training data, to provide a reward signal for the reinforcement learning. The simulator may be non-differentiable simulator, for example a computer program to produce an image or audio waveform or a program to control a robot or vehicle.