Meta-Reinforcement Learning for Adaptive Autonomous Driving

Anonymous

Keywords: Deep reinforcement learning, Meta-learning, Autonomous driving, Carla simulator

Abstract: Reinforcement learning (RL) methods achieved major advances in multiple tasks surpassing human performance. However, most of RL strategies show a certain degree of weakness and may become computationally intractable when dealing with high-dimensional and non-stationary environments. In this paper, we build a meta-reinforcement learning (MRL) method embedding an adaptive neural network (NN) controller for efficient policy iteration in changing task conditions. Our main goal is to extend RL application to the challenging task of urban autonomous driving in CARLA simulator.

TL;DR: A meta-reinforcement learning approach embedding a neural network controller applied to autonomous driving with Carla simulator.