_pred = q_pred – gamma * dq_pred
q_target = q_target – gamma * dq_target
The update equations above suggests that both q_pred and q_target will be reduced by a factor of gamma.
_pred = q_pred – gamma * dq_pred
q_target = q_target – gamma * dq_target
The update equations above suggests that both q_pred and q_target will be reduced by a factor of gamma.