Reinforcement Learning: An Introduction (second edition)
Richard S. Sutton and Andrew G. Barto, “Reinforcement Learning: An Introduction (second edition)”. Second edition, MIT Press (published 2018). Used as a secondary history (section 1.7 and chapter notes) and for a defining statement.
- 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 Richard S. Sutton and Andrew G. Barto.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2018.
- Exact source
- Reinforcement Learning: An Introduction (second edition) MIT Press; author-hosted PDF (incompleteideas.net) · published 2018 · Retrieved for the candidate pack on 2026-10-29 (SHA-256 2dd0d71d9ee883fbeb99f9b888c65ac3255fae2512203d11b18e838befffe9a6). Author-hosted PDF of the second edition, copyright 2018, 2020 (CC BY-NC-ND 2.0). Ligatures such as "ff" are mis-encoded in the text layer; quotations avoid them.
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.
Explicitly credits · 1
People or institutions this document expressly credits, with the scope stated in each record.
- Marvin MinskyAccording to Sutton and Barto (2018), Minsky's 1954 PhD dissertation discussed computational models of reinforcement learning and described an analog machine built from components he called SNARCs.2018 · publication · Stated in source · Supported Inspect claim & evidence ↗Marvin Minsky: person page →
Attributes ideas to · 2
Works to which this document attributes an argument, concept, term, finding or approach, in its own words. Each attribution is this document’s claim, not evidence of origin or influence.
- Some Studies in Machine Learning Using the Game of CheckersAccording to Sutton and Barto (2018), Samuel (1959) proposed and implemented a learning method that included temporal-difference ideas, in his checkers-playing program.2018 · publication · Stated in source · Supported Inspect claim & evidence ↗Some Studies in Machine Learning Using the Game of Checkers: document page →
- Learning from Delayed RewardsAccording to Sutton and Barto (2018), the off-policy temporal-difference control algorithm known as Q-learning is due to Watkins (1989).2018 · publication · Stated in source · Supported Inspect claim & evidence ↗Learning from Delayed Rewards: document page →
Discusses · 2
Concepts explicitly discussed. No earliest use, invention or transmission is claimed.
- Evolutionary computationSutton and Barto (2018) distinguish reinforcement-learning methods, which use value functions, from evolutionary methods that search directly in policy space guided by evaluations of entire policies.2018 · publication · Stated in source · Supported Rests on reportingInspect claim & evidence ↗
- Reinforcement learningSutton and Barto (2018) define reinforcement learning as learning how to map situations to actions so as to maximise a numerical reward signal, without being told which actions to take.2018 · publication · Stated in source · Supported Inspect claim & evidence ↗
Not recorded for this document: cites · cited by · 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.