Cooperative Lane Changing via Deep Reinforcement Learning
This work addresses traffic efficiency for autonomous vehicles, but it appears incremental as it builds on existing deep reinforcement learning methods with a focus on cooperative rewards.
The paper tackled the problem of learning lane-changing strategies for autonomous vehicles using deep reinforcement learning, showing that cooperative reward design improves overall traffic efficiency compared to individual-focused approaches.
In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning. We show that the reward of the system should consider the overall traffic efficiency instead of the travel efficiency of an individual vehicle. In summary, cooperation leads to a more harmonic and efficient traffic system rather than competition