-
Notifications
You must be signed in to change notification settings - Fork 9
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
Added SAC agents #337
Added SAC agents #337
Conversation
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.
Some minor comments. Otherwise, LGTM. Could you also add the link to the results?
hive/agents/qnets/sac_heads.py
Outdated
|
||
class CategoricalPolicyHead(torch.nn.Module): | ||
"""A module that implements a discrete actor head. It uses the ouput from | ||
the :obj:`actor_net`, and adds creates a |
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.
typo?
start_method: "fork" | ||
tags: | ||
- benchmark_sac | ||
|
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.
remove?
hive/agents/sac.py
Outdated
action, _, _ = self._actor(observation) | ||
action = action.cpu().detach().numpy() | ||
action = self.unscale_actions(action) | ||
# action = action |
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.
What this comment is for?
Link to results comparing with CleanRL: https://api.wandb.ai/links/dapatil211/1df29fog |
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.
LGTM
No description provided.