Method and system for training autonomous driving agent on basis of deep reinforcement learning

Abstract

Disclosed are a method and a system for training an autonomous driving agent on the basis of deep reinforcement learning (DRL). The agent training method according to one embodiment may comprise a step of training an agent through an actor-critic algorithm in a simulation for DRL. The step of training may include inputting first information to an actor network to determine an action of the agent, and inputting second information to a critic to evaluate how helpful the action is to maximizing a reward in the actor-critic algorithm, the second information comprising the first information and additional information.