Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic

Maneuvering in dense traffic is a challenging task for autonomous vehicles\nbecause it requires reasoning about the stochastic behaviors of many other\nparticipants. In addition, the agent must achieve the maneuver within a limited\ntime and distance. In this work, we propose a combination of reinforcement\nlearning and game theory to learn merging behaviors. We design a training\ncurriculum for a reinforcement learning agent using the concept of level-$k$\nbehavior. This approach exposes the agent to a broad variety of behaviors\nduring training, which promotes learning policies that are robust to model\ndiscrepancies. We show that our approach learns more efficient policies than\ntraditional training methods.\n