PerishLab/emlearn
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

RL-0: exact policy learning from bandit reward #7

Merged
perishadmin merged 1 commit from land/emlearn-rl-zero into main 2026-08-03 18:26:40 +00:00
Conversation 0 Commits 1 Files changed 14 +746 -6
perishadmin commented 2026-08-03 18:24:50 +00:00
Contributor
Copy link

Adds exact rational EML policy parameters, a three-channel Banditron with one-shot correctness feedback, deterministic exploration, held-out radial transfer, frozen-policy ablation, CLI evidence, and explicit claim limits.

Adds exact rational EML policy parameters, a three-channel Banditron with one-shot correctness feedback, deterministic exploration, held-out radial transfer, frozen-policy ablation, CLI evidence, and explicit claim limits.
RL-0: exact policy learning from bandit reward
All checks were successful
guard / guard (pull_request) Successful in 1m39s
Details
guard / guard (push) Successful in 1m35s
Details
4a5d721ac4 
Adds exact rational EML policy parameters, a three-channel Banditron with one-shot correctness feedback, deterministic exploration, held-out radial transfer, frozen-policy ablation, CLI evidence, and explicit claim limits.

Land-Source: emlearn-rl-zero@b55afbb449c1a27e1e86e90757dfabd229f29368
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
PerishLab/emlearn!7
No description provided.