Skip to content

Implemented the rewards hyperparameters#31

Open
TheoCUC wants to merge 1 commit into
gbionics:mainfrom
TheoCUC:rewards-ratio
Open

Implemented the rewards hyperparameters#31
TheoCUC wants to merge 1 commit into
gbionics:mainfrom
TheoCUC:rewards-ratio

Conversation

@TheoCUC

@TheoCUC TheoCUC commented Sep 12, 2025

Copy link
Copy Markdown

In some cases, adjusting the ratio of Task reward to Style reward can better control the humanoid robot. Therefore, the hyperparameters marked as TODO in amp_on_policy_runner.py have been implemented in the algorithm's configuration file, and an example has been provided.

@GiulioRomualdi GiulioRomualdi left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for the contribution!

Comment thread example/agents_config.py
slow_down_factor = 1.0

def __post_init__(self):
self.algorithm.class_name = "AMP_PPO" No newline at end of file

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
self.algorithm.class_name = "AMP_PPO"
self.algorithm.class_name = "AMP_PPO"

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants