Update README.md

Author: mveres01

README.md

@@ -10,6 +10,23 @@ Currently, Traveling Salesman Problems and Vehicle Routing Problems are supporte
 * pytorch=0.4.1
 * matplotlib
 
+# To Run
+
+Run by calling ```python trainer.py```
+
+Tasks and complexity can be changed through the "task" and "nodes" flag:
+
+```python trainer.py --task=vrp --nodes=10```
+
+To restore a checkpoint, you must specify the path to a folder that has "actor.pt" and "critic.pt" checkpoints. Sample weights can be found [here](https://drive.google.com/open?id=1wxccGStVglspW-qIpUeMPXAGHh2HsFpF)
+
+```python trainer.py --task=vrp --nodes=10 --checkpoint=vrp10```
+## Differences from paper:
+
+* Uses a GRU instead of LSTM for the decoder network
+* Critic takes the raw static and dynamic input states and predicts a reward
+* Here we use demand scaling (MAX_DEMAND / MAX_VEHICLE_CAPACITY), and give the depot for the VRP a negative value proportionaly to the missing capacity (Unsure if used or not)
+
 ## TSP Sample Tours:
 
 __Left__: TSP with 20 cities 
@@ -33,22 +50,7 @@ __Right__: VRP with 20 cities + load 30
 </p>
 
 
-# To Run
-
-Run by calling ```python trainer.py```
-
-Tasks and complexity can be changed through the "task" and "nodes" flag:
-
-```python trainer.py --task=vrp --nodes=10```
 
-To restore a checkpoint, you must specify the path to a folder that has "actor.pt" and "critic.pt" checkpoints. Sample weights can be found [here](https://drive.google.com/open?id=1wxccGStVglspW-qIpUeMPXAGHh2HsFpF)
-
-```python trainer.py --task=vrp --nodes=10 --checkpoint=vrp10```
-## Differences from paper:
-
-* Uses a GRU instead of LSTM for the decoder network
-* Critic takes the raw static and dynamic input states and predicts a reward
-* (Unsure) Here we use demand scaling (MAX_DEMAND / MAX_VEHICLE_CAPACITY), and give the depot for the VRP a negative value proportionaly to the missing capacity
 
 # TSP