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

07/16/2019

∙

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 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 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 leverage the trained policy and its weights to the reinforcement learning phase for which we use DDPG. This combination shows a considerable performance boost comparing to both pure imitation learning and pure DDPG for the autonomous driving task.

READ FULL TEXT

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

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Action-Conditioned Contrastive Policy Pretraining

Integrating Imitation Learning with Human Driving Data into Reinforcement Learning to Improve Training Efficiency for Autonomous Driving

End-to-end Driving Deploying through Uncertainty-Aware Imitation Learning and Stochastic Visual Domain Adaptation

Evaluation of MPC-based Imitation Learning for Human-like Autonomous Driving

Robust Behavioral Cloning for Autonomous Vehicles using End-to-End Imitation Learning

Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture

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

Related Research

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Action-Conditioned Contrastive Policy Pretraining

Integrating Imitation Learning with Human Driving Data into Reinforcement Learning to Improve Training Efficiency for Autonomous Driving

End-to-end Driving Deploying through Uncertainty-Aware Imitation Learning and Stochastic Visual Domain Adaptation

Evaluation of MPC-based Imitation Learning for Human-like Autonomous Driving

Robust Behavioral Cloning for Autonomous Vehicles using End-to-End Imitation Learning

Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture