Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281484278> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4281484278 abstract "We revisit the incremental autonomous exploration problem proposed by Lim & Auer (2012). In this setting, the agent aims to learn a set of near-optimal goal-conditioned policies to reach the $L$-controllable states: states that are incrementally reachable from an initial state $s_0$ within $L$ steps in expectation. We introduce a new algorithm with stronger sample complexity bounds than existing ones. Furthermore, we also prove the first lower bound for the autonomous exploration problem. In particular, the lower bound implies that our proposed algorithm, Value-Aware Autonomous Exploration, is nearly minimax-optimal when the number of $L$-controllable states grows polynomially with respect to $L$. Key in our algorithm design is a connection between autonomous exploration and multi-goal stochastic shortest path, a new problem that naturally generalizes the classical stochastic shortest path problem. This new problem and its connection to autonomous exploration can be of independent interest." @default.
- W4281484278 created "2022-05-26" @default.
- W4281484278 creator A5033061754 @default.
- W4281484278 creator A5061905935 @default.
- W4281484278 creator A5087617696 @default.
- W4281484278 date "2022-05-21" @default.
- W4281484278 modified "2023-09-28" @default.
- W4281484278 title "Near-Optimal Algorithms for Autonomous Exploration and Multi-Goal Stochastic Shortest Path" @default.
- W4281484278 doi "https://doi.org/10.48550/arxiv.2205.10729" @default.
- W4281484278 hasPublicationYear "2022" @default.
- W4281484278 type Work @default.
- W4281484278 citedByCount "0" @default.
- W4281484278 crossrefType "posted-content" @default.
- W4281484278 hasAuthorship W4281484278A5033061754 @default.
- W4281484278 hasAuthorship W4281484278A5061905935 @default.
- W4281484278 hasAuthorship W4281484278A5087617696 @default.
- W4281484278 hasBestOaLocation W42814842781 @default.
- W4281484278 hasConcept C11413529 @default.
- W4281484278 hasConcept C126255220 @default.
- W4281484278 hasConcept C132525143 @default.
- W4281484278 hasConcept C13355873 @default.
- W4281484278 hasConcept C149728462 @default.
- W4281484278 hasConcept C177264268 @default.
- W4281484278 hasConcept C199360897 @default.
- W4281484278 hasConcept C22590252 @default.
- W4281484278 hasConcept C2524010 @default.
- W4281484278 hasConcept C26517878 @default.
- W4281484278 hasConcept C2777735758 @default.
- W4281484278 hasConcept C33923547 @default.
- W4281484278 hasConcept C38652104 @default.
- W4281484278 hasConcept C41008148 @default.
- W4281484278 hasConcept C48103436 @default.
- W4281484278 hasConcept C80444323 @default.
- W4281484278 hasConceptScore W4281484278C11413529 @default.
- W4281484278 hasConceptScore W4281484278C126255220 @default.
- W4281484278 hasConceptScore W4281484278C132525143 @default.
- W4281484278 hasConceptScore W4281484278C13355873 @default.
- W4281484278 hasConceptScore W4281484278C149728462 @default.
- W4281484278 hasConceptScore W4281484278C177264268 @default.
- W4281484278 hasConceptScore W4281484278C199360897 @default.
- W4281484278 hasConceptScore W4281484278C22590252 @default.
- W4281484278 hasConceptScore W4281484278C2524010 @default.
- W4281484278 hasConceptScore W4281484278C26517878 @default.
- W4281484278 hasConceptScore W4281484278C2777735758 @default.
- W4281484278 hasConceptScore W4281484278C33923547 @default.
- W4281484278 hasConceptScore W4281484278C38652104 @default.
- W4281484278 hasConceptScore W4281484278C41008148 @default.
- W4281484278 hasConceptScore W4281484278C48103436 @default.
- W4281484278 hasConceptScore W4281484278C80444323 @default.
- W4281484278 hasLocation W42814842781 @default.
- W4281484278 hasLocation W42814842782 @default.
- W4281484278 hasOpenAccess W4281484278 @default.
- W4281484278 hasPrimaryLocation W42814842781 @default.
- W4281484278 hasRelatedWork W1970871823 @default.
- W4281484278 hasRelatedWork W2008042368 @default.
- W4281484278 hasRelatedWork W2046916960 @default.
- W4281484278 hasRelatedWork W2134492883 @default.
- W4281484278 hasRelatedWork W2366250615 @default.
- W4281484278 hasRelatedWork W2386835479 @default.
- W4281484278 hasRelatedWork W2391412785 @default.
- W4281484278 hasRelatedWork W4229964315 @default.
- W4281484278 hasRelatedWork W4313304367 @default.
- W4281484278 hasRelatedWork W2469944050 @default.
- W4281484278 isParatext "false" @default.
- W4281484278 isRetracted "false" @default.
- W4281484278 workType "article" @default.