Graph Reinforcement Learning
Welcome to Graph RL
How does it work?
Graph RL lets you visualize the training process of a reinforcement learning agent trying to find the shortest path in a graph.
At first, the agent uses random choices to try to explore the graph
As the Agent lands on a Node, it gets rewarded based on the node's probability of being in the shortest path. It then calculates a q-value for every node in the graph.
The shortest path consists of the nodes with the best q-values
How to play?
1- Click on two nodes to select a starting and ending point
2- Choose the number of iterations
3- Train it
Legend
A
Node the Agent is currently on
B
Neighbors of the current Node
Edge is in shortest path
Select the number of iterations