sotayamashita/repro-understanding-the-performance-gap-in-preference-learning-a-dichotomy-of-rlhf-and-dpo
Upload pages/executive-summary/page.md with huggingface_hub
Upload pages/conclusion/page.md with huggingface_hub
Upload pages/claim-4-sparse-reward-estimation-has-a-statistical-advantage/page.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload pages/index.md with huggingface_hub
Upload pages/claim-3-rlhf-dominates-dpo-under-a-weak-policy-class/page.md with huggingface_hub
Upload pages/claim-2-online-dpo-can-strictly-outperform-offline-dpo/page.md with huggingface_hub
Upload pages/claim-1-isomorphic-classes-make-offline-rlhf-and-dpo-equivalent/page.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload README.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload logbook.json with huggingface_hub
Upload workspace.json with huggingface_hub
Upload pages/executive-summary/page.md with huggingface_hub
Upload pages/conclusion/page.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload pages/executive-summary/page.md with huggingface_hub
Upload pages/conclusion/page.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload pages/executive-summary/page.md with huggingface_hub
Upload pages/conclusion/page.md with huggingface_hub
Upload pages/claim-4-sparse-reward-estimation-has-a-statistical-advantage/page.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload README.md with huggingface_hub
Upload logbook.json with huggingface_hub
Upload README.md with huggingface_hub
Upload folder using huggingface_hub
Update logbook: Reproduction: Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
initial commit