The use of $\tanh$ is because it fits the described problem (rspecially for values that are min-max normalized). I have worked on couple of professional RL projects (specifically, with actions in the continuous space) and I did not use $\tanh$ at all.

the use of Tanh is purely because it fits the described problem (Especially for values that are min-max normalized). I have worked on couple of professional RL projects ( specifically with actions in the continuous space) and I did not use tanh at all. Hope that helped :)

the use of Tanh is purely because it fits the described problem (Especially for values that are min-max normalized). I have worked on couple of professional RL projects ( specifically with actions in the continuous space) and I did not use tanh at all. Hope that helped :)

The use of $\tanh$ is because it fits the described problem (rspecially for values that are min-max normalized). I have worked on couple of professional RL projects (specifically, with actions in the continuous space) and I did not use $\tanh$ at all.