Skip to content

Customize random strategy#468

Merged
younik merged 8 commits intomasterfrom
fix-strategy
Feb 5, 2026
Merged

Customize random strategy#468
younik merged 8 commits intomasterfrom
fix-strategy

Conversation

@younik
Copy link
Collaborator

@younik younik commented Feb 5, 2026

Allow to define the random strategy space from the args

@younik younik requested a review from josephdviviano February 5, 2026 14:26
younik and others added 6 commits February 5, 2026 15:39
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
Copy link
Collaborator

@josephdviviano josephdviviano left a comment

Choose a reason for hiding this comment

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

looks good! one question

"temperature": temperature,
"n_noisy_layers": n_noisy_layers,
"noisy_std_init": noisy_std_init,
}
Copy link
Collaborator

Choose a reason for hiding this comment

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

Cool! Can we fix any of these settings? I.e., only sample temperature, leaving n_noisy_layers=0 and epsilon=0 for all agents?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

yes, exactly, by setting std=0, we only "sample" the mean

@younik younik merged commit 3c2fd22 into master Feb 5, 2026
2 of 4 checks passed
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