Deep Reinforcement Learning with Mixed Convolutional Network

摘要

Recent research has shown that map raw pixels from a single front-facing camera directly to steering commands are surprisingly powerful. This paper presents a convolutional neural network (CNN) to playing the CarRacing-v0 using imitation learning in OpenAI Gym. The dataset is generated by playing the game manually in Gym and used a data augmentation method to expand the dataset to 4 times larger than before. Also, we read the true speed, four ABS sensors, steering wheel position, and gyroscope for each image and designed a mixed model by combining the sensor input and image input. After training, this model can automatically detect the boundaries of road features and drive the robot like a human. By comparing with AlexNet and VGG16 using the average reward in CarRacing-v0, our model wins the maximum overall system performance.