Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912432356> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2912432356 abstract "We present a novel method for learning a set of disentangled reward functions that sum to the original environment reward and are constrained to be independently obtainable. We define independent obtainability in terms of value functions with respect to obtaining one learned reward while pursuing another learned reward. Empirically, we illustrate that our method can learn meaningful reward decompositions in a variety of domains and that these decompositions exhibit some form of generalization performance when the environment's reward is modified. Theoretically, we derive results about the effect of maximizing our method's objective on the resulting reward functions and their corresponding optimal policies." @default.
- W2912432356 created "2019-02-21" @default.
- W2912432356 creator A5045742904 @default.
- W2912432356 creator A5046052093 @default.
- W2912432356 date "2019-01-24" @default.
- W2912432356 modified "2023-09-27" @default.
- W2912432356 title "Learning Independently-Obtainable Reward Functions" @default.
- W2912432356 cites W1513468570 @default.
- W2912432356 cites W1541109270 @default.
- W2912432356 cites W1594201624 @default.
- W2912432356 cites W2110906765 @default.
- W2912432356 cites W2121863487 @default.
- W2912432356 cites W2134779831 @default.
- W2912432356 cites W2136202932 @default.
- W2912432356 cites W2145339207 @default.
- W2912432356 cites W2559823555 @default.
- W2912432356 cites W2604626881 @default.
- W2912432356 cites W2624731731 @default.
- W2912432356 cites W2737047298 @default.
- W2912432356 cites W2751258126 @default.
- W2912432356 cites W2753738274 @default.
- W2912432356 cites W2810132790 @default.
- W2912432356 cites W2952161038 @default.
- W2912432356 cites W2963226019 @default.
- W2912432356 cites W2964184826 @default.
- W2912432356 hasPublicationYear "2019" @default.
- W2912432356 type Work @default.
- W2912432356 sameAs 2912432356 @default.
- W2912432356 citedByCount "2" @default.
- W2912432356 countsByYear W29124323562019 @default.
- W2912432356 countsByYear W29124323562020 @default.
- W2912432356 crossrefType "posted-content" @default.
- W2912432356 hasAuthorship W2912432356A5045742904 @default.
- W2912432356 hasAuthorship W2912432356A5046052093 @default.
- W2912432356 hasConcept C119857082 @default.
- W2912432356 hasConcept C134306372 @default.
- W2912432356 hasConcept C136197465 @default.
- W2912432356 hasConcept C154945302 @default.
- W2912432356 hasConcept C177148314 @default.
- W2912432356 hasConcept C177264268 @default.
- W2912432356 hasConcept C199360897 @default.
- W2912432356 hasConcept C2776291640 @default.
- W2912432356 hasConcept C33923547 @default.
- W2912432356 hasConcept C41008148 @default.
- W2912432356 hasConceptScore W2912432356C119857082 @default.
- W2912432356 hasConceptScore W2912432356C134306372 @default.
- W2912432356 hasConceptScore W2912432356C136197465 @default.
- W2912432356 hasConceptScore W2912432356C154945302 @default.
- W2912432356 hasConceptScore W2912432356C177148314 @default.
- W2912432356 hasConceptScore W2912432356C177264268 @default.
- W2912432356 hasConceptScore W2912432356C199360897 @default.
- W2912432356 hasConceptScore W2912432356C2776291640 @default.
- W2912432356 hasConceptScore W2912432356C33923547 @default.
- W2912432356 hasConceptScore W2912432356C41008148 @default.
- W2912432356 hasLocation W29124323561 @default.
- W2912432356 hasOpenAccess W2912432356 @default.
- W2912432356 hasPrimaryLocation W29124323561 @default.
- W2912432356 hasRelatedWork W2162009473 @default.
- W2912432356 hasRelatedWork W2202549229 @default.
- W2912432356 hasRelatedWork W2364302853 @default.
- W2912432356 hasRelatedWork W2417936402 @default.
- W2912432356 hasRelatedWork W2605369401 @default.
- W2912432356 hasRelatedWork W2890882194 @default.
- W2912432356 hasRelatedWork W2897200624 @default.
- W2912432356 hasRelatedWork W2903017298 @default.
- W2912432356 hasRelatedWork W2915060045 @default.
- W2912432356 hasRelatedWork W2970181117 @default.
- W2912432356 hasRelatedWork W3035599863 @default.
- W2912432356 hasRelatedWork W3092156990 @default.
- W2912432356 hasRelatedWork W3121174195 @default.
- W2912432356 hasRelatedWork W3153101054 @default.
- W2912432356 hasRelatedWork W3163049241 @default.
- W2912432356 hasRelatedWork W3171639171 @default.
- W2912432356 hasRelatedWork W3208494958 @default.
- W2912432356 hasRelatedWork W3211380950 @default.
- W2912432356 hasRelatedWork W88199814 @default.
- W2912432356 hasRelatedWork W3112800872 @default.
- W2912432356 isParatext "false" @default.
- W2912432356 isRetracted "false" @default.
- W2912432356 magId "2912432356" @default.
- W2912432356 workType "article" @default.