Q Learning Demo

Instructions

Start: Initiates the simulation with the selected settings. The default simulation speed is set at 1x.
Speed Adjustment: Alter the simulation speed using the slider control provided.
Reset: Resets the simulation to its initial setup and parameters.
Grid Size Adjustment: Change the grid size using the dropdown menu below.
Creating Obstacles: Click once on any cell in the left grid to designate it as an obstacle.
Modifying Rewards: Double-click a cell to cycle its state from green (reward: +1) to red (penalty: -1) and then back to its normal state.
Grid Animation: The left grid visually demonstrates the cell being used to compute the state value, which is then highlighted in the right grid.

Calculation of Q values of (state, action) pair appears here

Previous Iteration

Iterations :

Steps :

Discount Factor :

0.9

Epsilon :

0.3

Learning Rate :

0.1

Reward :

-0.1

Grid Size :

Min.Speed Max.Speed