Matches in SemOpenAlex for { <https://semopenalex.org/work/W3005727454> ?p ?o ?g. }
- W3005727454 abstract "Can algorithms with a representation solve reinforcement learning problems? In this work, we answer this question in the affirmative, where we take simple learning to be tabular Q-Learning, the good representations to be a learned state abstraction, and challenging to be continuous control tasks. Our main contribution is a learning algorithm that abstracts a continuous state-space into a discrete one. We transfer this learned representation to unseen problems to enable effective learning. We provide theory showing that learned abstractions maintain a bounded value loss, and we report experiments showing that the abstractions empower tabular Q-Learning to learn efficiently in unseen tasks." @default.
- W3005727454 created "2020-02-24" @default.
- W3005727454 creator A5009722403 @default.
- W3005727454 creator A5037667167 @default.
- W3005727454 creator A5080191195 @default.
- W3005727454 date "2020-02-08" @default.
- W3005727454 modified "2023-09-23" @default.
- W3005727454 title "Learning State Abstractions for Transfer in Continuous Control." @default.
- W3005727454 cites W107583932 @default.
- W3005727454 cites W1164749991 @default.
- W3005727454 cites W1492014007 @default.
- W3005727454 cites W1492518272 @default.
- W3005727454 cites W1589991875 @default.
- W3005727454 cites W1640646391 @default.
- W3005727454 cites W171213352 @default.
- W3005727454 cites W1726275262 @default.
- W3005727454 cites W1944672 @default.
- W3005727454 cites W2024668293 @default.
- W3005727454 cites W2079247031 @default.
- W3005727454 cites W2084838588 @default.
- W3005727454 cites W2097381042 @default.
- W3005727454 cites W2097498341 @default.
- W3005727454 cites W2100677568 @default.
- W3005727454 cites W2109910161 @default.
- W3005727454 cites W2109952767 @default.
- W3005727454 cites W2119567691 @default.
- W3005727454 cites W2121517924 @default.
- W3005727454 cites W2121863487 @default.
- W3005727454 cites W2125074935 @default.
- W3005727454 cites W2125510930 @default.
- W3005727454 cites W2129442128 @default.
- W3005727454 cites W2132057084 @default.
- W3005727454 cites W2133458291 @default.
- W3005727454 cites W2133853511 @default.
- W3005727454 cites W2158548602 @default.
- W3005727454 cites W2160371091 @default.
- W3005727454 cites W2169743339 @default.
- W3005727454 cites W2174786457 @default.
- W3005727454 cites W21891419 @default.
- W3005727454 cites W2190606234 @default.
- W3005727454 cites W2397240726 @default.
- W3005727454 cites W2397253692 @default.
- W3005727454 cites W2468354762 @default.
- W3005727454 cites W2550182557 @default.
- W3005727454 cites W2579923771 @default.
- W3005727454 cites W2735575534 @default.
- W3005727454 cites W2787666871 @default.
- W3005727454 cites W2790355818 @default.
- W3005727454 cites W2803178532 @default.
- W3005727454 cites W2808418668 @default.
- W3005727454 cites W2896834494 @default.
- W3005727454 cites W2904715276 @default.
- W3005727454 cites W2919115771 @default.
- W3005727454 cites W2926786214 @default.
- W3005727454 cites W2962708723 @default.
- W3005727454 cites W2962717849 @default.
- W3005727454 cites W2963199420 @default.
- W3005727454 cites W2963611966 @default.
- W3005727454 cites W2964118262 @default.
- W3005727454 cites W2964121744 @default.
- W3005727454 cites W2964220198 @default.
- W3005727454 cites W3093010610 @default.
- W3005727454 cites W3139460557 @default.
- W3005727454 cites W99485931 @default.
- W3005727454 cites W2131600418 @default.
- W3005727454 hasPublicationYear "2020" @default.
- W3005727454 type Work @default.
- W3005727454 sameAs 3005727454 @default.
- W3005727454 citedByCount "3" @default.
- W3005727454 countsByYear W30057274542020 @default.
- W3005727454 countsByYear W30057274542021 @default.
- W3005727454 crossrefType "posted-content" @default.
- W3005727454 hasAuthorship W3005727454A5009722403 @default.
- W3005727454 hasAuthorship W3005727454A5037667167 @default.
- W3005727454 hasAuthorship W3005727454A5080191195 @default.
- W3005727454 hasConcept C105795698 @default.
- W3005727454 hasConcept C111472728 @default.
- W3005727454 hasConcept C111919701 @default.
- W3005727454 hasConcept C11413529 @default.
- W3005727454 hasConcept C119857082 @default.
- W3005727454 hasConcept C124304363 @default.
- W3005727454 hasConcept C134306372 @default.
- W3005727454 hasConcept C138885662 @default.
- W3005727454 hasConcept C150899416 @default.
- W3005727454 hasConcept C154945302 @default.
- W3005727454 hasConcept C17744445 @default.
- W3005727454 hasConcept C199539241 @default.
- W3005727454 hasConcept C2775924081 @default.
- W3005727454 hasConcept C2776359362 @default.
- W3005727454 hasConcept C2778572836 @default.
- W3005727454 hasConcept C2780586882 @default.
- W3005727454 hasConcept C33923547 @default.
- W3005727454 hasConcept C34388435 @default.
- W3005727454 hasConcept C41008148 @default.
- W3005727454 hasConcept C48103436 @default.
- W3005727454 hasConcept C72434380 @default.
- W3005727454 hasConcept C80444323 @default.
- W3005727454 hasConcept C94625758 @default.
- W3005727454 hasConcept C97541855 @default.
- W3005727454 hasConceptScore W3005727454C105795698 @default.