Ch3_book.ipynb list3.3

[HyeonhoonLee]

state2 is already reshaped in

"
state2_ = game.board.render_np().reshape(1,64) + np.random.rand(1,64)/10.0
state2 = torch.from_numpy(state2_).float() #L
"

Therefore,

with torch.no_grad():
newQ = model(state2.reshape(1,64))
maxQ = torch.max(newQ) #M

might be fixed as:

with torch.no_grad():
newQ = model(state2)
maxQ = torch.max(newQ) #M