Revision History
Temporal-difference learning · 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 claims that AlphaGo, AlphaGo Zero and AlphaZero trained their value networks with TD (they regressed on final game outcomes; only MuZero's Atari setting uses bootstrapped TD targets), restored the exact wording of the Sutton and Barto quote, and fixed the dating and features of TD-Gammon version 1.0 (plus 7 minor fixes)
Version 7 · Nov 4, 2026, 10:32 PM
- Improve internal links (2026-10-13)
Version 6 · Oct 13, 2026, 10:19 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:29 PM
- Render formulas with LaTeX math notation
Version 4 · Jul 11, 2026, 06:09 PM