Revision History
Proximal Policy Optimization (PPO) · 6 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 claims that Sparrow, Llama 3, Llama 4, Bard and Gemini used PPO or GRPO, unsourced GRPO memory-saving figures, a misstated Atari comparison with ACER, an invented gradient-clipping value attributed to the PPO paper, wrong dates for OpenAI Five, Claude and Phi-3, and the wrong author name for a 2025 implementation study (plus 14 minor fixes)
Version 6 · Nov 2, 2026, 08:08 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:03 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:31 PM