{"entities":[{"id":"reinforcement-learning","name":"Reinforcement learning","type":"concept"},{"id":"th-tesauro-1995","name":"Temporal Difference Learning and TD-Gammon","type":"document","subtype":"Journal article","description":"Gerald Tesauro, “Temporal Difference Learning and TD-Gammon”. Communications of the ACM 38 (3) (published March 1995). Read in a later HTML transcription.","sourceIds":["source-th-d-tesauro-1995"]}],"claims":[{"id":"th-rl-tesauro-1995-1991-games","subject":"th-tesauro-1995","predicate":"states_provision","object":{"kind":"literal","value":"In late 1991 TD-Gammon 1.0 played 51 games against Bill Robertie, Paul Magriel and Malcolm Davis, with a net loss of 13 points."},"topic":"ideas","statement":"Tesauro (1995) states that in late 1991 TD-Gammon version 1.0 played 51 games against Robertie, Magriel and Malcolm Davis, with a net loss of 13 points.","time":{"kind":"event","date":"1995-03","basis":"publication","note":"Date of the stating text; the event it reports is dated \"late 1991\"."},"resolution":"supported","evidenceIds":["evidence-th-rl-tesauro-1995-1991-games-1","evidence-th-rl-tesauro-1995-1991-games-2"],"attributes":{"provision":{"kind":"statement","key":"rl-tesauro-1995-1991-games"}}},{"id":"th-rl-tesauro-1995-1992-debut","subject":"th-tesauro-1995","predicate":"states_provision","object":{"kind":"literal","value":"TD-Gammon 2.0 made its public debut at the 1992 World Cup of Backgammon tournament."},"topic":"ideas","statement":"Tesauro (1995) states that TD-Gammon 2.0 made its public debut at the 1992 World Cup of Backgammon, losing a net 7 points over 38 exhibition games against top players.","time":{"kind":"event","date":"1995-03","basis":"publication","note":"Date of the stating text; the event it reports is dated 1992."},"resolution":"supported","evidenceIds":["evidence-th-rl-tesauro-1995-1992-debut-1","evidence-th-rl-tesauro-1995-1992-debut-2","evidence-th-rl-tesauro-1995-1992-debut-3"],"attributes":{"provision":{"kind":"statement","key":"rl-tesauro-1995-1992-debut"}}},{"id":"th-ml-tesauro-1995","subject":"th-tesauro-1995","predicate":"uses_term","object":{"kind":"entity","entityId":"th-term-machine-learning"},"topic":"ideas","statement":"Tesauro (1995) names board games as a testing ground for approaches in \"artificial intelligence and machine learning\".","time":{"kind":"event","date":"1995-03","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-ml-tesauro-1995-1"],"attributes":{"naming":{"string":"machine learning","sense":"meets","role":"use","register":"nonfiction","reading":"text"}}},{"id":"th-rl-tesauro-1995-def","subject":"th-tesauro-1995","predicate":"discusses","object":{"kind":"entity","entityId":"reinforcement-learning"},"topic":"ideas","statement":"Tesauro (1995) describes TD-Gammon as a neural network that trains itself as a backgammon evaluation function by self-play, developed to explore ideas in reinforcement learning, whose basic paradigm he sets out.","time":{"kind":"event","date":"1995-03","basis":"publication","note":"Date of publication, as the source gives it."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-th-rl-tesauro-1995-def-1","evidence-th-rl-tesauro-1995-def-2"],"attributes":{"technical":{"kind":"definition"}}}],"sources":[{"id":"source-th-d-tesauro-1995","documentId":"th-tesauro-1995","title":"Temporal Difference Learning and TD-Gammon","authors":["Gerald Tesauro"],"publisher":"Communications of the ACM (HTML transcription by Tom Keith on bkgm.com, copied with permission of the ACM as the page states)","publicationDate":"1995-03","version":"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.","evidenceUrl":"https://bkgm.com/articles/tesauro/tdl.html","language":"en"}],"evidence":[{"id":"evidence-th-rl-tesauro-1995-1991-games-1","claimId":"th-rl-tesauro-1995-1991-games","sourceId":"source-th-d-tesauro-1995","support":"supports","locator":"section \"Results of Training\"","passage":"In late 1991, version 1.0 played a total of 51 games against Robertie, Magriel, and Malcolm Davis","passageType":"quote"},{"id":"evidence-th-rl-tesauro-1995-1992-debut-1","claimId":"th-rl-tesauro-1995-1992-debut","sourceId":"source-th-d-tesauro-1995","support":"supports","locator":"section \"Results of Training\"","passage":"made its public debut at the 1992 World Cup of Backgammon tournament. In 38 exhibition games against top human players","passageType":"quote"},{"id":"evidence-th-ml-tesauro-1995-1","claimId":"th-ml-tesauro-1995","sourceId":"source-th-d-tesauro-1995","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-tesauro-1995-def-1","claimId":"th-rl-tesauro-1995-def","sourceId":"source-th-d-tesauro-1995","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-th-rl-tesauro-1995-def-2","claimId":"th-rl-tesauro-1995-def","sourceId":"source-th-d-tesauro-1995","support":"supports","verification":"machine_checked","retrievalRoute":"direct"}],"at":{"entities":[126,1573],"claims":[4742,4743,4817,4822],"sources":[1490],"evidence":[6204,6206,6303,6311,6312]},"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"}