Q-learning agent - 2D gridworld

Episode 0

Step 0

Last return -

Success (50) -

Epsilon -

Greedy path -

Mean V(s) 0

Updates 0

Graph: episode return (dots) and 20-episode average (line).

Hover or touch a tile to inspect its Q-values.

Paint pits instead of walls Show greedy policy arrows

Drag across tiles to paint or erase walls; drag the green goal or blue start. Q(s,a) += alpha [r + gamma max Q(s',a') - Q(s,a)] (Watkins & Dayan 1992).