TRAINING A NEURAL NETWORK TO CONTROL AN AGENT USING TASK-RELEVANT ADVERSARIAL IMITATION LEARNINGA method is proposed of training a neural network to generate action data for controlling an agent to perform a task in an environment. The method includes obtaining, for each of a plurality of ...
TRAINING A NEURAL NETWORK TO CONTROL AN AGENT USING TASK-RELEVANT ADVERSARIAL IMITATION LEARNINGA method is proposed of training a neural network to generate action data for controlling an agent to perform a task in an environment. The method includes obtaining, for each of a plurality of ...