In Ex. 2, under the details of the task description in the read me file, I believe that there is a typo in the formulation of the torque reward formula. It is set as:
Torque torque_reward: $\text{exp}(- w_{\tau}\Vert \mathbf{\tau} \Vert_2^2 / (2 N \sigma_t^2))$
But I believe it should be:
Torque torque_reward: $w_{\tau}\text{exp}(-\Vert \mathbf{\tau} \Vert_2^2 / (2 N \sigma_t^2))$
In Ex. 2, under the details of the task description in the read me file, I believe that there is a typo in the formulation of the torque reward formula. It is set as:
torque_reward
: $\text{exp}(- w_{\tau}\Vert \mathbf{\tau} \Vert_2^2 / (2 N \sigma_t^2))$But I believe it should be:
torque_reward
: $w_{\tau}\text{exp}(-\Vert \mathbf{\tau} \Vert_2^2 / (2 N \sigma_t^2))$Could confirm or deny my suspicion?