Support for mixed discrete-continuous actions #856
Unanswered
CloudyDory
asked this question in
Q&A
Replies: 1 comment 2 replies
-
|
imo you only need to inherit PPOPolicy and rewrite parts of them (forward, learn) to let it support combined action input. No need to rewrite Collector and Trainer |
Beta Was this translation helpful? Give feedback.
2 replies
-
|
Hi, I guess the collector should also be rewritten as well? |
Beta Was this translation helpful? Give feedback.
-
|
I don't think so. You can pack your action as a dict (similar to dict action space) each time, which will be converted to |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi, I have a custom environment that needs to input both discrete and continuous actions. The continuous action should be a Gaussian policy with learned mean and standard deviation. I hope to train a PPO agent to solve the task. Is it still possible to use Tianshou's default Collector and OnPolicyTrainer, or should I write my custom Collector and OnPolicyTrainer?
Beta Was this translation helpful? Give feedback.
All reactions