What is T in this code

dW2 = (a1.T).dot(delta3)

Thank you

]]>Question: What algorithm will find the optimal policy and maximise rewards along the way to balance the exploration vs exploitation tradeoff?

thanks.

]]>http://s0.wp.com/latex.php?zoom=1.25&latex=%5Cbegin%7Baligned%7D++%5Cfrac%7B%5Cpartial+E_3%7D%7B%5Cpartial+W%7D+%26%3D+%5Csum%5Climits_%7Bk%3D0%7D%5E%7B3%7D+%5Cfrac%7B%5Cpartial+E_3%7D%7B%5Cpartial+%5Chat%7By%7D_3%7D%5Cfrac%7B%5Cpartial%5Chat%7By%7D_3%7D%7B%5Cpartial+s_3%7D++%5Cleft%28%5Cprod%5Climits_%7Bj%3Dk%2B1%7D%5E%7B3%7D++%5Cfrac%7B%5Cpartial+s_j%7D%7B%5Cpartial+s_%7Bj-1%7D%7D%5Cright%29++%5Cfrac%7B%5Cpartial+s_k%7D%7B%5Cpartial+W%7D%5C%5C++%5Cend%7Baligned%7D++&bg=ffffff&fg=000&s=0 ]]>