Wumpus-QLearning

𝑒𝑝𝑠𝑖𝑙𝑜𝑛 = 0.5

𝑑𝑖𝑠𝑐𝑜𝑢𝑛𝑡 𝑓𝑎𝑐𝑡𝑜𝑟 = 0.9

episodes = 700

goal reward = +100

hole or wall reward = -100

others = -1

first page:

first element: green square , goal
second element: blue square , start
third and fourth elements: red square , hole
fifth element: black square , wall

result: