{"entities":[{"id":"reinforcement-learning","name":"Reinforcement learning","type":"concept"},{"id":"marvin-minsky","name":"Marvin Minsky","type":"person"},{"id":"th-sutton-barto-2018","name":"Reinforcement Learning: An Introduction (second edition)","type":"document","subtype":"Book","description":"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.","sourceIds":["source-th-d-suttonbarto-2018"]},{"id":"th-samuel-1959","name":"Some Studies in Machine Learning Using the Game of Checkers","type":"document"},{"id":"th-watkins-1989","name":"Learning from Delayed Rewards","type":"document"},{"id":"th-fam-evolutionary","name":"Evolutionary computation","type":"concept"}],"claims":[{"id":"th-rl-sb-credits-minsky-1954","subject":"th-sutton-barto-2018","predicate":"explicitly_credits","object":{"kind":"entity","entityId":"marvin-minsky"},"topic":"ideas","statement":"According 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.","time":{"kind":"event","date":"2018","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-rl-sb-credits-minsky-1954-1"]},{"id":"th-rl-sb-def","subject":"th-sutton-barto-2018","predicate":"discusses","object":{"kind":"entity","entityId":"reinforcement-learning"},"topic":"ideas","statement":"Sutton 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.","time":{"kind":"event","date":"2018","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-rl-sb-def-1","evidence-th-rl-sb-def-2"],"attributes":{"technical":{"kind":"definition"}}},{"id":"th-evo-sb-contrast","subject":"th-sutton-barto-2018","predicate":"discusses","object":{"kind":"entity","entityId":"th-fam-evolutionary"},"topic":"ideas","statement":"Sutton 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.","time":{"kind":"event","date":"2018","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-evo-sb-contrast-1"],"attributes":{"technical":{"kind":"definition"}}},{"id":"th-rl-sb-credits-samuel","subject":"th-sutton-barto-2018","predicate":"credits_work","object":{"kind":"entity","entityId":"th-samuel-1959"},"topic":"ideas","statement":"According to Sutton and Barto (2018), Samuel (1959) proposed and implemented a learning method that included temporal-difference ideas, in his checkers-playing program.","time":{"kind":"event","date":"2018","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-rl-sb-credits-samuel-1","evidence-th-rl-sb-credits-samuel-2"],"attributes":{"attribution":"attributes_term"}},{"id":"th-rl-sb-credits-watkins","subject":"th-sutton-barto-2018","predicate":"credits_work","object":{"kind":"entity","entityId":"th-watkins-1989"},"topic":"ideas","statement":"According to Sutton and Barto (2018), the off-policy temporal-difference control algorithm known as Q-learning is due to Watkins (1989).","time":{"kind":"event","date":"2018","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-rl-sb-credits-watkins-1","evidence-th-rl-sb-credits-watkins-2"],"attributes":{"attribution":"attributes_term"}}],"sources":[{"id":"source-th-d-suttonbarto-2018","documentId":"th-sutton-barto-2018","title":"Reinforcement Learning: An Introduction (second edition)","authors":["Richard S. Sutton","Andrew G. Barto"],"publisher":"MIT Press; author-hosted PDF (incompleteideas.net)","publicationDate":"2018","version":"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.","evidenceUrl":"http://incompleteideas.net/book/RLbook2020.pdf","language":"en"}],"evidence":[{"id":"evidence-th-rl-sb-credits-minsky-1954-1","claimId":"th-rl-sb-credits-minsky-1954","sourceId":"source-th-d-suttonbarto-2018","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-sb-def-1","claimId":"th-rl-sb-def","sourceId":"source-th-d-suttonbarto-2018","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-sb-def-2","claimId":"th-rl-sb-def","sourceId":"source-th-d-suttonbarto-2018","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-evo-sb-contrast-1","claimId":"th-evo-sb-contrast","sourceId":"source-th-d-suttonbarto-2018","sourceRole":"secondary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-sb-credits-samuel-1","claimId":"th-rl-sb-credits-samuel","sourceId":"source-th-d-suttonbarto-2018","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-sb-credits-samuel-2","claimId":"th-rl-sb-credits-samuel","sourceId":"source-th-d-suttonbarto-2018","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-sb-credits-watkins-1","claimId":"th-rl-sb-credits-watkins","sourceId":"source-th-d-suttonbarto-2018","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-sb-credits-watkins-2","claimId":"th-rl-sb-credits-watkins","sourceId":"source-th-d-suttonbarto-2018","support":"supports","verification":"machine_checked","retrievalRoute":"direct"}],"at":{"entities":[126,901,1572,1617,1628,1660],"claims":[4741,4821,4835,4899,4900],"sources":[1489],"evidence":[6203,6309,6310,6331,6417,6418,6419,6420]},"index":{"byClaim":[],"marks":[],"chronicle":{"years":[{"year":1863,"topics":{"ideas":5},"stated":0},{"year":1865,"topics":{"ideas":1},"stated":0},{"year":1872,"topics":{"ideas":7},"stated":0},{"year":1943,"topics":{"ideas":1},"stated":0},{"year":1947,"topics":{"ideas":2},"stated":0},{"year":1950,"topics":{"ideas":7},"stated":0},{"year":1951,"topics":{"ideas":5},"stated":0},{"year":1952,"topics":{"ideas":2},"stated":0},{"year":1955,"topics":{"ideas":31},"stated":0},{"year":1956,"topics":{"ideas":1},"stated":0},{"year":1957,"topics":{"ideas":1},"stated":0},{"year":1958,"topics":{"ideas":3},"stated":0},{"year":1959,"topics":{"ideas":6},"stated":0},{"year":1960,"topics":{"ideas":11},"stated":0},{"year":1961,"topics":{"ideas":10},"stated":0},{"year":1965,"topics":{"ideas":8},"stated":0},{"year":1966,"topics":{"ideas":20},"stated":0},{"year":1968,"topics":{"ideas":5},"stated":0},{"year":1969,"topics":{"ideas":2},"stated":0},{"year":1971,"topics":{"ideas":4},"stated":0},{"year":1972,"topics":{"ideas":1},"stated":0},{"year":1973,"topics":{"ideas":2},"stated":0},{"year":1974,"topics":{"ideas":2},"stated":0},{"year":1975,"topics":{"ideas":1},"stated":0},{"year":1976,"topics":{"ideas":1},"stated":0},{"year":1977,"topics":{"people":2,"ideas":8},"stated":0},{"year":1979,"topics":{"ideas":4},"stated":0},{"year":1980,"topics":{"ideas":2},"stated":0},{"year":1981,"topics":{"people":2},"stated":0},{"year":1982,"topics":{"ideas":4},"stated":0},{"year":1983,"topics":{"ideas":4},"stated":0},{"year":1984,"topics":{"ideas":21},"stated":0},{"year":1985,"topics":{"ideas":9},"stated":0},{"year":1986,"topics":{"ideas":18},"stated":0},{"year":1987,"topics":{"ideas":1},"stated":0},{"year":1988,"topics":{"ideas":6},"stated":0},{"year":1989,"topics":{"ideas":8},"stated":0},{"year":1990,"topics":{"ideas":5},"stated":0},{"year":1991,"topics":{"ideas":11},"stated":0},{"year":1992,"topics":{"ideas":9},"stated":0},{"year":1993,"topics":{"ideas":14,"people":3},"stated":0},{"year":1994,"topics":{"ideas":14},"stated":0},{"year":1995,"topics":{"ideas":10,"people":1},"stated":0},{"year":1996,"topics":{"ideas":71},"stated":0},{"year":1997,"topics":{"ideas":12},"stated":0},{"year":1998,"topics":{"ideas":49},"stated":0},{"year":1999,"topics":{"ideas":27,"people":1,"institutions":1},"stated":0},{"year":2000,"topics":{"ideas":62},"stated":0},{"year":2001,"topics":{"ideas":39},"stated":0},{"year":2002,"topics":{"ideas":30},"stated":0},{"year":2003,"topics":{"ideas":8},"stated":0},{"year":2004,"topics":{"ideas":12,"people":3},"stated":0},{"year":2005,"topics":{"ideas":10,"people":1},"stated":0},{"year":2006,"topics":{"ideas":26,"people":1},"stated":0},{"year":2007,"topics":{"ideas":20},"stated":0},{"year":2008,"topics":{"ideas":57,"people":3,"institutions":1},"stated":0},{"year":2009,"topics":{"ideas":10,"people":1},"stated":0},{"year":2010,"topics":{"people":3,"ideas":11,"institutions":1,"governance":4},"stated":0},{"year":2011,"topics":{"people":3,"ideas":7,"institutions":2},"stated":0},{"year":2012,"topics":{"people":4,"ideas":17,"institutions":2},"stated":0},{"year":2013,"topics":{"ideas":46,"people":4,"institutions":2,"capital":1},"stated":0},{"year":2014,"topics":{"institutions":2,"ideas":54,"people":5},"stated":0},{"year":2015,"topics":{"people":22,"ideas":122,"institutions":3,"capital":1},"stated":0},{"year":2016,"topics":{"ideas":88,"people":2},"stated":0},{"year":2017,"topics":{"people":16,"institutions":2,"ideas":128,"governance":2},"stated":0},{"year":2018,"topics":{"people":8,"ideas":158,"institutions":8,"governance":1},"stated":0},{"year":2019,"topics":{"capital":1,"compute":1,"people":10,"governance":19,"ideas":175,"institutions":4},"stated":0},{"year":2020,"topics":{"people":6,"ideas":98,"institutions":1,"governance":2},"stated":0},{"year":2021,"topics":{"people":27,"ideas":177,"compute":1,"institutions":23,"governance":4,"capital":6},"stated":0},{"year":2022,"topics":{"people":15,"ideas":217,"institutions":6,"governance":3,"compute":2,"capital":1},"stated":0},{"year":2023,"topics":{"capital":5,"compute":7,"institutions":23,"people":51,"governance":179,"ideas":389},"stated":0},{"year":2024,"topics":{"capital":12,"compute":19,"governance":282,"people":80,"ideas":178,"institutions":28},"stated":1},{"year":2025,"topics":{"governance":547,"compute":69,"capital":34,"people":90,"institutions":18,"ideas":178},"stated":7},{"year":2026,"topics":{"governance":442,"capital":8,"compute":32,"institutions":21,"ideas":91,"people":107},"stated":19},{"year":2027,"topics":{},"stated":9},{"year":2028,"topics":{},"stated":6},{"year":2029,"topics":{},"stated":3},{"year":2030,"topics":{},"stated":3},{"year":2032,"topics":{},"stated":2},{"year":2035,"topics":{},"stated":2},{"year":2039,"topics":{},"stated":1},{"year":2042,"topics":{},"stated":1},{"year":2050,"topics":{},"stated":1}],"scheduled":[],"statedBy":[]},"collections":[{"target":{"kind":"propositions","id":"superintelligence"},"title":"Propositions about superintelligence, 1863–2022","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"risk-debate"},"title":"Arguments about catastrophic risk from advanced AI","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"yudkowsky-arguments"},"title":"Eliezer Yudkowsky’s arguments on common claims about AI, 1996–2026","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"economics-of-machine-intelligence"},"title":"Economics of machine intelligence","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"orbital-compute-arguments"},"title":"Arguments about compute in orbit","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"ai-bio-arguments"},"title":"Arguments about AI and biological risk","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"ai-in-science"},"title":"AI in science","claimIds":[],"records":[]},{"target":{"kind":"documents"},"title":"Frontier safety frameworks","claimIds":[]},{"target":{"kind":"compare","id":"frontier-safety-frameworks"},"title":"Compare frameworks","claimIds":[]},{"target":{"kind":"control","id":"openai"},"title":"OpenAI’s control structure, 2015–2026","claimIds":[]},{"target":{"kind":"control","id":"anthropic"},"title":"Anthropic’s control structure, 2021–2026","claimIds":[]},{"target":{"kind":"commitments"},"title":"External commitments and obligations","claimIds":[]},{"target":{"kind":"question","id":"frameworks-to-obligations"},"title":"Frameworks, commitments and legal obligations, 2023–2026","claimIds":[]},{"target":{"kind":"reading"},"title":"Founding and early leadership","claimIds":[]}]},"version":"131evrz"}