Matches in SemOpenAlex for { <https://semopenalex.org/work/W2942500381> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2942500381 abstract "Recently, world-class human players have been outperformed in a number of complex two-person games (Go, Chess, Checkers) by Deep Reinforcement Learning systems. However, the data efficiency of the learning systems is unclear given that they appear to require far more training games to achieve such performance than any human player might experience in a lifetime. In addition, the resulting learned strategies are not in a form which can be communicated to human players. This contrasts to earlier research in Behavioural Cloning in which single-agent skills were machine learned in a symbolic language, facilitating their being taught to human beings. In this paper, we consider Machine Discovery of human-comprehensible strategies for simple two-person games (Noughts-and-Crosses and Hexapawn). One advantage of considering simple games is that there is a tractable approach to calculating minimax regret. We use these games to compare Cumulative Minimax Regret for variants of both standard and deep reinforcement learning against two variants of a new Meta-interpretive Learning system called MIGO. In our experiments, tested variants of both normal and deep reinforcement learning have consistently worse performance (higher cumulative minimax regret) than both variants of MIGO on Noughts-and-Crosses and Hexapawn. In addition, MIGO’s learned rules are relatively easy to comprehend, and are demonstrated to achieve significant transfer learning in both directions between Noughts-and-Crosses and Hexapawn." @default.
- W2942500381 created "2019-05-03" @default.
- W2942500381 creator A5070721694 @default.
- W2942500381 creator A5076917665 @default.
- W2942500381 date "2019-04-01" @default.
- W2942500381 modified "2023-09-24" @default.
- W2942500381 title "Machine Discovery of Comprehensible Strategies for Simple Games Using Meta-interpretive Learning" @default.
- W2942500381 cites W1490475971 @default.
- W2942500381 cites W1530558387 @default.
- W2942500381 cites W1543584403 @default.
- W2942500381 cites W1769664091 @default.
- W2942500381 cites W2091092523 @default.
- W2942500381 cites W2145339207 @default.
- W2942500381 cites W2159047538 @default.
- W2942500381 cites W2318460192 @default.
- W2942500381 cites W2394606514 @default.
- W2942500381 cites W2395903764 @default.
- W2942500381 cites W2802751390 @default.
- W2942500381 cites W2902907165 @default.
- W2942500381 cites W3020831056 @default.
- W2942500381 cites W4250129635 @default.
- W2942500381 doi "https://doi.org/10.1007/s00354-019-00054-2" @default.
- W2942500381 hasPublicationYear "2019" @default.
- W2942500381 type Work @default.
- W2942500381 sameAs 2942500381 @default.
- W2942500381 citedByCount "4" @default.
- W2942500381 countsByYear W29425003812020 @default.
- W2942500381 countsByYear W29425003812021 @default.
- W2942500381 crossrefType "journal-article" @default.
- W2942500381 hasAuthorship W2942500381A5070721694 @default.
- W2942500381 hasAuthorship W2942500381A5076917665 @default.
- W2942500381 hasBestOaLocation W29425003811 @default.
- W2942500381 hasConcept C107457646 @default.
- W2942500381 hasConcept C111472728 @default.
- W2942500381 hasConcept C119857082 @default.
- W2942500381 hasConcept C126255220 @default.
- W2942500381 hasConcept C138885662 @default.
- W2942500381 hasConcept C149728462 @default.
- W2942500381 hasConcept C154945302 @default.
- W2942500381 hasConcept C2777212361 @default.
- W2942500381 hasConcept C2780586882 @default.
- W2942500381 hasConcept C33923547 @default.
- W2942500381 hasConcept C41008148 @default.
- W2942500381 hasConcept C50817715 @default.
- W2942500381 hasConcept C97541855 @default.
- W2942500381 hasConceptScore W2942500381C107457646 @default.
- W2942500381 hasConceptScore W2942500381C111472728 @default.
- W2942500381 hasConceptScore W2942500381C119857082 @default.
- W2942500381 hasConceptScore W2942500381C126255220 @default.
- W2942500381 hasConceptScore W2942500381C138885662 @default.
- W2942500381 hasConceptScore W2942500381C149728462 @default.
- W2942500381 hasConceptScore W2942500381C154945302 @default.
- W2942500381 hasConceptScore W2942500381C2777212361 @default.
- W2942500381 hasConceptScore W2942500381C2780586882 @default.
- W2942500381 hasConceptScore W2942500381C33923547 @default.
- W2942500381 hasConceptScore W2942500381C41008148 @default.
- W2942500381 hasConceptScore W2942500381C50817715 @default.
- W2942500381 hasConceptScore W2942500381C97541855 @default.
- W2942500381 hasFunder F4320334627 @default.
- W2942500381 hasLocation W29425003811 @default.
- W2942500381 hasOpenAccess W2942500381 @default.
- W2942500381 hasPrimaryLocation W29425003811 @default.
- W2942500381 hasRelatedWork W1428984440 @default.
- W2942500381 hasRelatedWork W152102936 @default.
- W2942500381 hasRelatedWork W2109652022 @default.
- W2942500381 hasRelatedWork W2113363668 @default.
- W2942500381 hasRelatedWork W2123995443 @default.
- W2942500381 hasRelatedWork W2181388735 @default.
- W2942500381 hasRelatedWork W2186731336 @default.
- W2942500381 hasRelatedWork W2418598014 @default.
- W2942500381 hasRelatedWork W2760768709 @default.
- W2942500381 hasRelatedWork W2799869235 @default.
- W2942500381 hasRelatedWork W2900172492 @default.
- W2942500381 hasRelatedWork W2982315532 @default.
- W2942500381 hasRelatedWork W2996887765 @default.
- W2942500381 hasRelatedWork W2998481030 @default.
- W2942500381 hasRelatedWork W3001182513 @default.
- W2942500381 hasRelatedWork W3118881636 @default.
- W2942500381 hasRelatedWork W3122677547 @default.
- W2942500381 hasRelatedWork W3124900667 @default.
- W2942500381 hasRelatedWork W3180097248 @default.
- W2942500381 hasRelatedWork W789315506 @default.
- W2942500381 isParatext "false" @default.
- W2942500381 isRetracted "false" @default.
- W2942500381 magId "2942500381" @default.
- W2942500381 workType "article" @default.