Learning to Drive in a Day

Code

• github.com/ZexinLi0w0/R3
  pytorch★ 5
• github.com/nautilusPrime/autodrive_ddpg
  none★ 0
• github.com/araffin/learning-to-drive-in-5-minutes
  pytorch★ 0
• github.com/bryonkucharski/Learning-to-Drive-with-Reinforcement-Learning-and-Variational-Autoencoders
  pytorch★ 0
• github.com/ankur-rc/autodrive_ddpg
  none★ 0
• github.com/bitsauce/Carla-ppo
  tf★ 0
• github.com/B-C-WANG/ReinforcementLearningInAutoPilot
  none★ 0
• github.com/bryonkucharski/learning-to-drive-in-a-day-reproduction
  pytorch★ 0

Abstract

We demonstrate the first application of deep reinforcement learning to autonomous driving. From randomly initialised parameters, our model is able to learn a policy for lane following in a handful of training episodes using a single monocular image as input. We provide a general and easy to obtain reward: the distance travelled by the vehicle without the safety driver taking control. We use a continuous, model-free deep reinforcement learning algorithm, with all exploration and optimisation performed on-vehicle. This demonstrates a new framework for autonomous driving which moves away from reliance on defined logical rules, mapping, and direct supervision. We discuss the challenges and opportunities to scale this approach to a broader range of autonomous driving tasks.

Tasks

Reproductions