Deep Reinforcement Learning with Mixed Convolutional Network
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2018End-to-End Deep Imitation Learning: Robot Soccer Case Study
- 2025Imitation Learning for Autonomous Driving: Insights from Real-World Testing
- 2018Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
- 2021Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
- 2021RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning
- 2024Self-Driving Car Racing: Application of Deep Reinforcement Learning
- 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
- 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skills