Temporal Difference Learning and TD-Gammon
Gerald Tesauro, “Temporal Difference Learning and TD-Gammon”. Communications of the ACM 38 (3) (published March 1995). Read in a later HTML transcription.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Gerald Tesauro.
- Dates
- No date claim recorded yet. The source record gives the publication date as 1995-03.
- Exact source
- Temporal Difference Learning and TD-Gammon Communications of the ACM (HTML transcription by Tom Keith on bkgm.com, copied with permission of the ACM as the page states) · published 1995-03 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 beccd4d203cbd0c13f13d4bb80364fb7e3957ed0836cc16a63bd147685f9756b). Later HTML transcription of the March 1995 article; figures and tables not reproduced in text.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Discusses · 1
Concepts explicitly discussed. No earliest use, invention or transmission is claimed.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · reports evaluation of. A missing record does not show that the relation does not exist.
What the document states
A limited selection of what this document states, each with its passage. It describes the text, not whether anyone acted on it.
- StatementIn late 1991 TD-Gammon 1.0 played 51 games against Bill Robertie, Paul Magriel and Malcolm Davis, with a net loss of 13 points.“In late 1991, version 1.0 played a total of 51 games against Robertie, Magriel, and Malcolm Davis”section "Results of Training"Inspect claim & evidence ↗
- StatementTD-Gammon 2.0 made its public debut at the 1992 World Cup of Backgammon tournament.“made its public debut at the 1992 World Cup of Backgammon tournament. In 38 exhibition games against top human players”section "Results of Training"Inspect claim & evidence ↗