Closed thushv89 closed 6 years ago
The weights were being updated wrongly. If w is the weights of actor/critic and w' are the weights of target actor/critic, I was doing w' <- w' tau + (1-tau) w' instead of w' <- w tau + (1-tau) w'
The weights were being updated wrongly. If w is the weights of actor/critic and w' are the weights of target actor/critic, I was doing w' <- w' tau + (1-tau) w' instead of w' <- w tau + (1-tau) w'