Context-Aware Autonomous Driving Using Meta-Reinforcement Learning
Authors:
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 450-455
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 contrast, human are more comfortable with learning from little experience and adapting to unexpected perturbations. These differences are shaping the current research intending to guide agent policies and eschewing the above limits. 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. The proposed approach yields higher performance and faster learning capabilities than conventionally pre-trained and randomly initialized RL algorithms.Keywords
This publication has 19 references indexed in Scilit:
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Reinforcement learning and optimal adaptive control: An overview and implementation examplesAnnual Reviews in Control, 2012
- Universal Meta-Learning Architecture and Algorithms2011
- Meta-Learning - Concepts and Techniques2009
- A Meta-Learning Method to Select the Kernel Width in Support Vector RegressionMachine Learning, 2004
- Meta-neural networks that learn by learning2003
- No free lunch theorems for optimizationIEEE Transactions on Evolutionary Computation, 1997
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992
- The Algorithm Selection Problem1976