ApolloRL: a Reinforcement Learning Platform for Autonomous Driving
This provides a domain-specific tool for researchers in autonomous driving, but it is incremental as it builds on existing methods and data.
The authors tackled the need for a comprehensive platform for reinforcement learning research in autonomous driving by introducing ApolloRL, which includes a closed-loop pipeline with training, simulation, and evaluation, and they reported performance results for baseline agents like PPO and SAC using 300 hours of real-world data.
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving. The platform provides a complete closed-loop pipeline with training, simulation, and evaluation components. It comes with 300 hours of real-world data in driving scenarios and popular baselines such as Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents. We elaborate in this paper on the architecture and the environment defined in the platform. In addition, we discuss the performance of the baseline agents in the ApolloRL environment.