Matches in SemOpenAlex for { <https://semopenalex.org/work/W125536345> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W125536345 abstract "Hutter's optimal universal but incomputable AIXI agent models the environment as an initially unknown probability distributioncomputing program. Once the latter is found through (incomputable) exhaustive search, classical planning yields an optimal policy. Here we reverse the roles of agent and environment by assuming a computable optimal policy realizable as a program mapping histories to actions. This assumption is powerful for two reasons: (1) The environment need not be probabilistically computable, which allows for dealing with truly stochastic environments, (2) All candidate policies are computable. In stochastic settings, our novel method Optimal Direct Policy Search (ODPS) identifies the best policy by direct universal search in the space of all possible computable policies. Unlike AIXI, it is computable, model-free, and does not require planning. We show that ODPS is optimal in the sense that its reward converges to the reward of the optimal policy in a very broad class of partially observable stochastic environments." @default.
- W125536345 created "2016-06-24" @default.
- W125536345 creator A5000470711 @default.
- W125536345 creator A5071172037 @default.
- W125536345 date "2011-01-01" @default.
- W125536345 modified "2023-09-23" @default.
- W125536345 title "Optimal Direct Policy Search" @default.
- W125536345 cites W1646752922 @default.
- W125536345 cites W2011058337 @default.
- W125536345 cites W2059023668 @default.
- W125536345 cites W2101684037 @default.
- W125536345 cites W2117726420 @default.
- W125536345 doi "https://doi.org/10.1007/978-3-642-22887-2_6" @default.
- W125536345 hasPublicationYear "2011" @default.
- W125536345 type Work @default.
- W125536345 sameAs 125536345 @default.
- W125536345 citedByCount "2" @default.
- W125536345 countsByYear W1255363452016 @default.
- W125536345 countsByYear W1255363452021 @default.
- W125536345 crossrefType "book-chapter" @default.
- W125536345 hasAuthorship W125536345A5000470711 @default.
- W125536345 hasAuthorship W125536345A5071172037 @default.
- W125536345 hasBestOaLocation W1255363452 @default.
- W125536345 hasConcept C126255220 @default.
- W125536345 hasConcept C139719470 @default.
- W125536345 hasConcept C154945302 @default.
- W125536345 hasConcept C162324750 @default.
- W125536345 hasConcept C20522121 @default.
- W125536345 hasConcept C2777212361 @default.
- W125536345 hasConcept C33923547 @default.
- W125536345 hasConcept C41008148 @default.
- W125536345 hasConceptScore W125536345C126255220 @default.
- W125536345 hasConceptScore W125536345C139719470 @default.
- W125536345 hasConceptScore W125536345C154945302 @default.
- W125536345 hasConceptScore W125536345C162324750 @default.
- W125536345 hasConceptScore W125536345C20522121 @default.
- W125536345 hasConceptScore W125536345C2777212361 @default.
- W125536345 hasConceptScore W125536345C33923547 @default.
- W125536345 hasConceptScore W125536345C41008148 @default.
- W125536345 hasLocation W1255363451 @default.
- W125536345 hasLocation W1255363452 @default.
- W125536345 hasOpenAccess W125536345 @default.
- W125536345 hasPrimaryLocation W1255363451 @default.
- W125536345 hasRelatedWork W1505198957 @default.
- W125536345 hasRelatedWork W1604050834 @default.
- W125536345 hasRelatedWork W1629423284 @default.
- W125536345 hasRelatedWork W2022783922 @default.
- W125536345 hasRelatedWork W2091872464 @default.
- W125536345 hasRelatedWork W2099215724 @default.
- W125536345 hasRelatedWork W2149551746 @default.
- W125536345 hasRelatedWork W2156874884 @default.
- W125536345 hasRelatedWork W2558819991 @default.
- W125536345 hasRelatedWork W2807018115 @default.
- W125536345 hasRelatedWork W2908154496 @default.
- W125536345 hasRelatedWork W2918548974 @default.
- W125536345 hasRelatedWork W2946522670 @default.
- W125536345 hasRelatedWork W2950677922 @default.
- W125536345 hasRelatedWork W2962836094 @default.
- W125536345 hasRelatedWork W2964986650 @default.
- W125536345 hasRelatedWork W3012335515 @default.
- W125536345 hasRelatedWork W3107471681 @default.
- W125536345 hasRelatedWork W3156930568 @default.
- W125536345 hasRelatedWork W3209382096 @default.
- W125536345 isParatext "false" @default.
- W125536345 isRetracted "false" @default.
- W125536345 magId "125536345" @default.
- W125536345 workType "book-chapter" @default.