Research map / Reinforcement learning / Policy gradient and actor-critic
DyETC: Dynamic Electronic Toll Collection for Traffic Congestion Alleviation
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 Beta-distribution policy instead of Normal-distribution policy (ablation) | PG-β · synthetic traffic network | traffic volume | Helped |
| use time-dependent policy/value functions instead of time-independent (PG-I) (ablation) | PG-β · synthetic traffic network | traffic volume | Helped |
| use separate per-period functions instead of adding time as a state dimension (PG-time) (ablation) | PG-β · synthetic traffic network | traffic volume | Helped |
| add state abstraction (PG-β-abs) (ablation) | PG-β · synthetic traffic network | traffic volume | No clear effect |
| add state abstraction (PG-β-abs) (ablation) | PG-β · synthetic traffic network | per-episode runtime | Helped |
| use PG-β dynamic tolls instead of Fix toll | DyETC · Singapore Central Region | traffic volume: +8% | Helped |
| use PG-β dynamic tolls instead of Δ-tolling | DyETC · Singapore Central Region | total travel time: -14.6% | Helped |
| use PG-β tolls vs existing schemes across demand, cost sensitivity, value of time, max toll | DyETC · synthetic traffic network | traffic volume and travel time | Helped |
Closest papers by meaning
- Pay Your Trip for Traffic Congestion: Dynamic Pricing in Traffic-Aware Road Networks (AAAI 2020 · similarity 0.85)
- Selecting Compliant Agents for Opt-in Micro-Tolling (AAAI 2019 · similarity 0.82)
- FairTP: A Prolonged Fairness Framework for Traffic Prediction (AAAI 2025 · similarity 0.80)
- QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers (NeurIPS 2024 · similarity 0.80)
- GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching (AAAI 2025 · similarity 0.79)
- Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning (AAAI 2024 · similarity 0.78)
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.