[Question] About the output layer of algorithms

[abdulkadrtr]

❓ Question

Hello, I am working on a project using SAC and PPO algorithms from stable-baselines3. I have connected my working environment to a gym environment, and for example, my action space is defined as self.action_space = spaces.Box(low=np.array([-2, 0]), high=np.array([2, 8]), dtype=np.float32) Do the algorithms I use adjust their output layer according to the defined action space? Specifically, what is used in the output layer of algorithms like SAC, PPO, and TD3?

Checklist

• [X] I have checked that there is no similar issue in the repo
• [X] I have read the documentation
• [X] If code there is, it is minimal and working
• [X] If code there is, it is formatted using the markdown code blocks for both code and stack traces.

[araffin]

https://stable-baselines3.readthedocs.io/en/master/guide/rl_tips.html#tips-and-tricks-when-creating-a-custom-environment and many related/duplicate issues. In general, I would recommend you to read more about PPO/SAC (we have link to resource in our doc).