… driving simulation platform called MetaDrive to support the research of generalizable
reinforcement learning … an infinite number of diverse driving scenarios from both the procedural …

… In the real world: we test 10 models listed in Table I on 9 driving scenarios. In total we report
results gathered over more than 400 test drives. See Section IV-B for a detailed description. …

… reinforcement learning and 2) introducing a framework for endend autonomous driving using
deep reinforcement learning to … learning dataset with exhaustive coverage of all scenarios. …

… CONCLUSION This paper presents a novel deep reinforcement learning based decision-making
structure for automated driving at intersections based on collected traffic images from …

… In all such scenarios we are aiming to solve a sequential decision … of reinforcement learning,
the taxonomy of tasks where RL is a promising solution especially in the domains of driving …

… scenarios that can be found. To deal with this problem, we provide a Deep Reinforcement
Learning approach for intersection handling, which is combined with Curriculum Learning to …

… To illustrate the idea, let us consider a challenging driving scenario, which we call the double
merge scenario (see Figure 1 for an illustration). In a double merge, vehicles approach the …

… scenarios while deploying and testing reinforcement learning(… autonomous driving agents
in complex intersection scenarios, … of RL for autonomous driving in the intersection scenario, …

… by deep reinforcement learning algorithms mostly happens in scenarios where controller …
case when applying deep reinforcement learning algorithms to autonomous driving system. For …

… -scenarios autonomous driving task. To solve this challenge, we propose a hierarchical
reinforcement learning structure to learn a … master policy between different driving styles policies. …