Loading...
Learning to Drive with Deep Reinforcement Learning
Author(s)
Date Issued
January 21, 2021
Type
Conference Paper
Abstract
Autonomous driving cars are important due to improved safety and fuel efficiency. Various techniques have been described to consider only a single task, for example, recognition, prediction, and planning with supervised learning techniques. Some limitations of previous studies are: (1) human bias from human demonstration; (2) the need for multiple components such as localization, road mapping etc. with a complicated fusion logic; (3) in reinforcement learning, the focus was mostly on the learning algorithms but less on the evaluation of different sensors and reward functions. We describe end-To-end reinforcement learning for an autonomous car, which used only a single reinforcement learning model to create the autonomous car. Further, we designed a new efficient reward function to make the agent learn faster (18% improvement for all settings compared to the baseline reward function) and build the car with only the necessary perceptions and sensors. We show that it performed better with state-of-The-Art off-policy reinforcement learning for continuous action (SAC, TD3).
Citation
Kst 2021 2021 13th International Conference Knowledge and Smart Technology, 147-152, 2021