AI Wiki

Revision History

Reinforcement Learning from Human Feedback (RLHF) · 11 revisions

Sizes are character counts of the article source. The signed number is the change from the previous revision.

Left column picks the older revision, right column the newer.
v11CurrentAI assisted32,015-48,908

Correction: replace an overextended catalogue with a source-bounded account of RLHF terminology, history, human feedback, reward modeling, PPO and non-PPO policy optimization, adjacent methods, evaluation, and limitations.

8d ago·Jul 28, 2026, 08:45 PM
v10AI assisted80,923+129

Added 6 contextual internal links

13d ago·Jul 23, 2026, 03:02 PM
v9AI assisted80,794+752

Render formulas with LaTeX math notation

25d ago·Jul 11, 2026, 09:28 PM
v8AI assisted80,042+6,098

Auto-saved before update

1mo ago·Jun 20, 2026, 08:37 AM
v7AI assisted73,944+52

Auto-saved before update

1mo ago·Jun 9, 2026, 07:25 PM
v6AI assisted73,892+15,862

Pre-update snapshot before enhancement to 10091 words.

2mo ago·May 18, 2026, 10:27 AM
v5AI assisted58,030-18

Auto-saved before bulk wikilink fix

3mo ago·Apr 26, 2026, 05:20 PM
v4AI assisted58,048+15

Auto-saved before bulk wikilink fix

3mo ago·Apr 26, 2026, 05:14 PM
v3AI assisted58,033-1,707

Auto-saved before update

4mo ago·Apr 7, 2026, 07:01 PM
v259,740+295

Edit details were not recorded

v1Page created59,445+59,445

Initial import from MediaWiki

4mo ago·Mar 19, 2026, 07:00 AM