Update README.md
Browse files
README.md
CHANGED
|
@@ -12,17 +12,17 @@ tags:
|
|
| 12 |
- sb3
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# GARRO: Graph-Aware Reinforcement Routing Optimizer (
|
| 16 |
|
| 17 |
GARRO is a Graph Neural Network (GNN)-enhanced Reinforcement Learning (RL) routing policy designed for optimal traffic engineering in dynamic network topologies. This repository contains the trained model parameters, evaluation summaries, and performance benchmarks evaluated on the **NSFNet** topology.
|
| 18 |
|
| 19 |
- **GitHub Repository:** [DanielAgbeni/GARRO](https://github.com/DanielAgbeni/GARRO)
|
| 20 |
- **Framework:** PyTorch / Stable-Baselines3
|
| 21 |
-
- **Topology:**
|
| 22 |
|
| 23 |
## Model Performance Benchmarks
|
| 24 |
|
| 25 |
-
Below is the comparative performance summary of GARRO against standard routing baselines (Random, ECMP, and OSPF) on the
|
| 26 |
|
| 27 |
| Algorithm | Mean Episode Reward (↑) | End-to-End Latency (ms) (↓) | Packet Delivery Ratio PDR (%) (↑) | Max Link Utilization (↓) |
|
| 28 |
| :--- | :--- | :--- | :--- | :--- |
|
|
|
|
| 12 |
- sb3
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# GARRO: Graph-Aware Reinforcement Routing Optimizer (NSFNET Topology)
|
| 16 |
|
| 17 |
GARRO is a Graph Neural Network (GNN)-enhanced Reinforcement Learning (RL) routing policy designed for optimal traffic engineering in dynamic network topologies. This repository contains the trained model parameters, evaluation summaries, and performance benchmarks evaluated on the **NSFNet** topology.
|
| 18 |
|
| 19 |
- **GitHub Repository:** [DanielAgbeni/GARRO](https://github.com/DanielAgbeni/GARRO)
|
| 20 |
- **Framework:** PyTorch / Stable-Baselines3
|
| 21 |
+
- **Topology:** NSFNET
|
| 22 |
|
| 23 |
## Model Performance Benchmarks
|
| 24 |
|
| 25 |
+
Below is the comparative performance summary of GARRO against standard routing baselines (Random, ECMP, and OSPF) on the NSFNET topology:
|
| 26 |
|
| 27 |
| Algorithm | Mean Episode Reward (↑) | End-to-End Latency (ms) (↓) | Packet Delivery Ratio PDR (%) (↑) | Max Link Utilization (↓) |
|
| 28 |
| :--- | :--- | :--- | :--- | :--- |
|