Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Multiagent Decision Making For Maritime Traffic Management
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 vessel-based value function (Vessel-PG) instead of REINFORCE-style PG with total returns (ablation) | traffic control policy · synthetic maritime instances | objective cost | Helped |
| Vessel-PG instead of DDPG | traffic control policy · synthetic, varying resource penalty w_r | resource violations | Helped |
| Vessel-PG instead of DDPG when w_r = 0 (no violation penalty) | traffic control policy · synthetic | average delay | No clear effect |
| increase resource capacity percentage | all methods · synthetic, 100 vessels | quality gap between methods | Mixed |
| policy input restricted to total counts in zones z and z' instead of full count tables (ablation) | Vessel-PG · synthetic and real | solution quality | Helped |
| apply Vessel-PG speed guidance during hours 4-6 at 60% capacity vs observed traffic | real traffic · AIS data, 10 busiest days | max resource violation | Helped |
| apply Vessel-PG speed guidance vs observed traffic | real traffic · AIS data, 8th hour | max resource violation | Hurt |
| apply Vessel-PG speed guidance vs observed traffic | real traffic · AIS data, longest west-east route | average travel time | Helped |
Closest papers by meaning
- Agentic AI for Digital Twin (AAAI 2025 · similarity 0.83)
- Online Guidance Graph Optimization for Lifelong Multi-Agent Path Finding (AAAI 2025 · similarity 0.81)
- Sequential Modeling of Complex Marine Navigation: Case Study on a Passenger Vessel (Student Abstract) (AAAI 2024 · similarity 0.81)
- Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding (AAAI 2024 · similarity 0.80)
- One Step is Enough: Multi-Agent Reinforcement Learning Based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms (NeurIPS 2026 · similarity 0.80)
- Scalable Safe Policy Improvement for Factored Multi-Agent MDPs (ICML 2024 · similarity 0.80)
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.