Revision History
Policy gradient methods · 7 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected a paraphrase presented as a Sutton et al. quote, an overstated Konda-Tsitsiklis convergence claim, the false claim that AlphaStar used PPO, OpenAI Five hardware figures taken from the 2018 system, a misattributed PPO implementation-details finding (Engstrom et al., not Ilyas et al.), an overstated Cassie result, and stale claims that PPO is still the dominant RLHF algorithm (plus 17 minor fixes)
Version 7 · Nov 4, 2026, 03:37 PM
- Update: added a video.
Version 6 · Nov 1, 2026, 08:25 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:19 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:29 PM
- Render formulas with LaTeX math notation
Version 3 · Jul 11, 2026, 09:28 PM