Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving | IEEE Conference Publication | IEEE Xplore

Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving


Abstract:

We present a training pipeline for the autonomous driving task given the current camera image and vehicle speed as the input to produce the throttle, brake, and steering ...Show More

Abstract:

We present a training pipeline for the autonomous driving task given the current camera image and vehicle speed as the input to produce the throttle, brake, and steering control output. The simulator Airsim's [1] convenient weather and lighting API provides a sufficient diversity during training which can be very helpful to increase the trained policy's robustness. In order to not limit the possible policy's performance, we use a continuous and deterministic control policy setting. We utilize ResNet-34 [2] as our actor and critic networks with some slight changes in the fully connected layers. Considering human's mastery of this task and the high-complexity nature of this task, we first use imitation learning to mimic the given human policy and then leverage the trained policy and its weights to the reinforcement learning phase for which we use DDPG [3]. This combination shows a considerable performance boost comparing to both pure imitation learning and pure DDPG for the autonomous driving task.
Date of Conference: 15-18 October 2019
Date Added to IEEE Xplore: 30 January 2020
ISBN Information:

ISSN Information:

Conference Location: Jeju, Korea (South)

Contact IEEE to Subscribe

References

References is not available for this document.