Summary of Rl-msa: a Reinforcement Learning-based Multi-line Bus Scheduling Approach, by Yingzhuo Liu
RL-MSA: a Reinforcement Learning-based Multi-line bus Scheduling Approach
by Yingzhuo Liu
First submitted to arxiv on: 11 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a Reinforcement Learning-based Multi-line bus Scheduling Approach (RL-MSA) to address the Multiple Line Bus Scheduling Problem (MLBSP). The approach models MLBSP as a Markov Decision Process (MDP) and learns a policy at both offline and online phases. At the offline phase, deadhead decision is integrated into bus selection decision for the first time. A bus priority screening mechanism is invented to construct bus-related features. A reward function combining final and step-wise rewards is devised considering the interests of both the bus company and passengers. The approach demonstrates reduced number of buses used compared with offline optimization approaches at the offline phase, while maintaining service quality without increasing operational cost at the online phase. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper solves a big problem that makes bus companies waste time and money by creating a better way to schedule buses. It uses special computer learning techniques called Reinforcement Learning to make decisions about which buses to use and when. The approach takes into account things like traffic congestion and tries to balance the needs of both the bus company and passengers. The result is a system that can efficiently schedule buses while still providing good service. |
Keywords
* Artificial intelligence * Optimization * Reinforcement learning
