-
Notifications
You must be signed in to change notification settings - Fork 24
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Reinforcement Learning Template #276
base: main
Are you sure you want to change the base?
Reinforcement Learning Template #276
Conversation
theory-in-progress
commented
Jul 12, 2023
- Added 2 algorithms for Reinforcement Learning: REINFORCE and Advantage Actor Critic (A2C)
- The Algorithms are implemented for the OpenAI Gym env: CarRacing-v2
- Added 2 algorithms for Reinforcement Learning: REINFORCE and Advantage Actor Critic (A2C) - The Algorithms are implemented for the OpenAI Gym env: CarRacing-v2
✅ Deploy Preview for code-generator ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
eps = np.finfo(np.float32).eps.item() | ||
|
||
|
||
class ActorCriticNetwork(nn.Module): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@theory-in-progress @vfdev-5 I think it would be better if we define the network in a separate file so that it can be edited easily. Also I was looking at torchrl
and I think it provides some abstactions over the contents of ActorCriticNetwork
. Should we use it ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yes, good point, I was also once thinking about torchrl and that we could use it. Thanks!
- DQN Template for CarRacing-v2 - Supports Rendering of video - Starts Giving Good results after ~100 Episodes
- Uses Advantage Actor Critic model using torchrl - Gym Environment: CarRacing-v2