Q-Learning Model Tables

Open Game View

State Picker

Current State

State

0

max_a Q(s,a)

0.000

Highest Policy Actions

RIGHT

Export Summary

Episodes:

Alpha:

Gamma:

Epsilon Start:

Epsilon Final:

Action Order:

Policy Matrix

Rows are states. Columns follow the exported action order.

Q Matrix

Tied maxima are highlighted in each row.