Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
SabaPivot
/
repro-success-conditioning
like
0
Running
App
Files
Files
Community
main
repro-success-conditioning
/
pages
1.18 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
SabaPivot
Expose four anchored success-conditioning claims
d00808f
verified
23 days ago
claim-1-chi-squared-trust-region-equivalence-prop-4-1
Update logbook: Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
29 days ago
claim-2-three-way-equality-at-every-state-prop-4-3-4-4
Update logbook: Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
29 days ago
claim-3-conservative-improvement-operator-cor-4-5
Update logbook: Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
29 days ago
claim-4-return-thresholding-misalignment-prop-7-1
Update logbook: Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
29 days ago
conclusion
Update logbook: Repro - Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
29 days ago
executive-summary
Expose four anchored success-conditioning claims
23 days ago
index.md
Safe
683 Bytes
Expose four anchored success-conditioning claims
23 days ago