Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950900511> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2950900511 abstract "Many researchers have explored methods for hierarchical reinforcement learning (RL) with temporal abstractions, in which abstract actions are defined that can perform many primitive actions before terminating. However, little is known about learning with state abstractions, in which aspects of the state space are ignored. In previous work, we developed the MAXQ method for hierarchical RL. In this paper, we define five conditions under which state abstraction can be combined with the MAXQ value function decomposition. We prove that the MAXQ-Q learning algorithm converges under these conditions and show experimentally that state abstraction is important for the successful application of MAXQ-Q learning." @default.
- W2950900511 created "2019-06-27" @default.
- W2950900511 creator A5074537073 @default.
- W2950900511 date "1999-05-21" @default.
- W2950900511 modified "2023-09-27" @default.
- W2950900511 title "State Abstraction in MAXQ Hierarchical Reinforcement Learning" @default.
- W2950900511 cites W1488730473 @default.
- W2950900511 cites W1576452626 @default.
- W2950900511 cites W1631187438 @default.
- W2950900511 cites W2012036715 @default.
- W2950900511 cites W2102000945 @default.
- W2950900511 cites W2150339816 @default.
- W2950900511 cites W2158548602 @default.
- W2950900511 cites W2165131254 @default.
- W2950900511 hasPublicationYear "1999" @default.
- W2950900511 type Work @default.
- W2950900511 sameAs 2950900511 @default.
- W2950900511 citedByCount "4" @default.
- W2950900511 countsByYear W29509005112016 @default.
- W2950900511 countsByYear W29509005112017 @default.
- W2950900511 crossrefType "posted-content" @default.
- W2950900511 hasAuthorship W2950900511A5074537073 @default.
- W2950900511 hasConcept C105795698 @default.
- W2950900511 hasConcept C111472728 @default.
- W2950900511 hasConcept C11413529 @default.
- W2950900511 hasConcept C119857082 @default.
- W2950900511 hasConcept C124304363 @default.
- W2950900511 hasConcept C124681953 @default.
- W2950900511 hasConcept C138885662 @default.
- W2950900511 hasConcept C14036430 @default.
- W2950900511 hasConcept C154945302 @default.
- W2950900511 hasConcept C18903297 @default.
- W2950900511 hasConcept C33923547 @default.
- W2950900511 hasConcept C41008148 @default.
- W2950900511 hasConcept C48103436 @default.
- W2950900511 hasConcept C72434380 @default.
- W2950900511 hasConcept C78458016 @default.
- W2950900511 hasConcept C86803240 @default.
- W2950900511 hasConcept C97541855 @default.
- W2950900511 hasConceptScore W2950900511C105795698 @default.
- W2950900511 hasConceptScore W2950900511C111472728 @default.
- W2950900511 hasConceptScore W2950900511C11413529 @default.
- W2950900511 hasConceptScore W2950900511C119857082 @default.
- W2950900511 hasConceptScore W2950900511C124304363 @default.
- W2950900511 hasConceptScore W2950900511C124681953 @default.
- W2950900511 hasConceptScore W2950900511C138885662 @default.
- W2950900511 hasConceptScore W2950900511C14036430 @default.
- W2950900511 hasConceptScore W2950900511C154945302 @default.
- W2950900511 hasConceptScore W2950900511C18903297 @default.
- W2950900511 hasConceptScore W2950900511C33923547 @default.
- W2950900511 hasConceptScore W2950900511C41008148 @default.
- W2950900511 hasConceptScore W2950900511C48103436 @default.
- W2950900511 hasConceptScore W2950900511C72434380 @default.
- W2950900511 hasConceptScore W2950900511C78458016 @default.
- W2950900511 hasConceptScore W2950900511C86803240 @default.
- W2950900511 hasConceptScore W2950900511C97541855 @default.
- W2950900511 hasLocation W29509005111 @default.
- W2950900511 hasOpenAccess W2950900511 @default.
- W2950900511 hasPrimaryLocation W29509005111 @default.
- W2950900511 hasRelatedWork W1218520990 @default.
- W2950900511 hasRelatedWork W1526807135 @default.
- W2950900511 hasRelatedWork W1540839255 @default.
- W2950900511 hasRelatedWork W1754881896 @default.
- W2950900511 hasRelatedWork W1976800061 @default.
- W2950900511 hasRelatedWork W2076490721 @default.
- W2950900511 hasRelatedWork W2087468775 @default.
- W2950900511 hasRelatedWork W2089561656 @default.
- W2950900511 hasRelatedWork W2121517924 @default.
- W2950900511 hasRelatedWork W2293184044 @default.
- W2950900511 hasRelatedWork W2356574896 @default.
- W2950900511 hasRelatedWork W2368063767 @default.
- W2950900511 hasRelatedWork W2372300130 @default.
- W2950900511 hasRelatedWork W2388624802 @default.
- W2950900511 hasRelatedWork W2540116300 @default.
- W2950900511 hasRelatedWork W256362207 @default.
- W2950900511 hasRelatedWork W2735325244 @default.
- W2950900511 hasRelatedWork W2798711120 @default.
- W2950900511 hasRelatedWork W2899685447 @default.
- W2950900511 hasRelatedWork W3035642820 @default.
- W2950900511 isParatext "false" @default.
- W2950900511 isRetracted "false" @default.
- W2950900511 magId "2950900511" @default.
- W2950900511 workType "article" @default.