Research map / Reinforcement learning / Visual and representation RL
A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use HRP instead of the compared algorithms | Mobike user-based rebalancing · Different budget levels | decreased un-service ratio: 43%-63% | Helped |
| Use HRP instead of the compared algorithms | Mobike user-based rebalancing · Different supply levels | decreased un-service ratio: 47%-60% | Helped |
| Use HRP instead of HRA and OPT-FIX | Mobike user-based rebalancing · 1 to 5 days | decreased un-service number | Helped |
| Use HRP instead of HRA | Mobike user-based rebalancing · 3×3 regions with highest request density | service level | Helped |
| Use HRP instead of HRA | Bike rebalancing policy transferred to unseen areas · Unseen Shanghai areas | decreased un-service ratio: 40%-80% | Helped |
| Use HRP instead of DDPG and HRA | Mobike user-based rebalancing · Training | training loss convergence | Helped |
| Use HRP instead of OPT-FIX | Mobike user-based rebalancing · End-of-day bike distribution | KL divergence: 0.598 -> 0.548 | Helped |
| Use HRP instead of Mobike's original system without monetary incentives | Mobike bike distribution · End-of-day bike distribution | KL divergence: 0.554 -> 0.548 | Helped |
Closest papers by meaning
- Mechanism Design with Predicted Task Revenue for Bike Sharing Systems (AAAI 2020 · similarity 0.86)
- One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms (NeurIPS 2026 · similarity 0.86)
- i-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance (AAAI 2024 · similarity 0.83)
- NondBREM: Nondeterministic Offline Reinforcement Learning for Large-Scale Order Dispatching (AAAI 2024 · similarity 0.82)
- Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems (NeurIPS 2025 · similarity 0.82)
- Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.