Q-Learning GridWorld Simulator
Environment Setup
Train Agent
Test Agent
Environment Setup
Train Agent
Test Agent
Grid Height
↺
3
8
Grid Width
↺
3
8
Setup Environment
Environment
Environment Info
4x4 GridWorld with start at (0,0) and goal at (3,3)
Learning Rate (α)
↺
0.01
1
Discount Factor (γ)
↺
0.1
1
Initial Exploration Rate (ε)
↺
0.1
1
Exploration Decay Rate
↺
0.9
0.999
Number of Episodes
↺
10
500
Train Agent
Training Environment
Training Metrics
Training Log
Test Trained Agent
Test Environment
Path Taken
Test Result