Matches in SemOpenAlex for { <https://semopenalex.org/work/W3127388429> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3127388429 abstract "Efficiently training agents with planning capabilities has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability on a given abstract 2-D occupancy map, like human navigation by reading a paper map, by treating it as an image. To learn this ability, we need to efficiently train an agent on environments with a small proportion of training maps and share knowledge effectively across the environments. We hypothesize that model-based navigation can better adapt an agent's behaviors to a task, since it disentangles the variations in map layout and goal location and enables longer-term planning ability on novel locations compared to reactive policies. We propose to learn a hypermodel that can understand patterns from a limited number of abstract maps and goal locations, to maximize alignment between the hypermodel predictions and real trajectories to extract information from multi-task off-policy experiences, and to construct denser feedback for planners by n-step goal relabelling. We train our approach on DeepMind Lab environments with layouts from different maps, and demonstrate superior performance on zero-shot transfer to novel maps and goals." @default.
- W3127388429 created "2021-02-15" @default.
- W3127388429 creator A5032791503 @default.
- W3127388429 creator A5035573979 @default.
- W3127388429 date "2021-05-04" @default.
- W3127388429 modified "2023-09-23" @default.
- W3127388429 title "Model-based Navigation in Environments with Novel Layouts Using Abstract 2-D Maps" @default.
- W3127388429 cites W2140135625 @default.
- W3127388429 cites W2171084228 @default.
- W3127388429 cites W2258731934 @default.
- W3127388429 cites W2336416123 @default.
- W3127388429 cites W2567015638 @default.
- W3127388429 cites W2914608873 @default.
- W3127388429 cites W2950872548 @default.
- W3127388429 cites W2963003879 @default.
- W3127388429 cites W2963946945 @default.
- W3127388429 cites W2963960193 @default.
- W3127388429 hasPublicationYear "2021" @default.
- W3127388429 type Work @default.
- W3127388429 sameAs 3127388429 @default.
- W3127388429 citedByCount "0" @default.
- W3127388429 crossrefType "journal-article" @default.
- W3127388429 hasAuthorship W3127388429A5032791503 @default.
- W3127388429 hasAuthorship W3127388429A5035573979 @default.
- W3127388429 hasConcept C107457646 @default.
- W3127388429 hasConcept C119857082 @default.
- W3127388429 hasConcept C120665830 @default.
- W3127388429 hasConcept C121332964 @default.
- W3127388429 hasConcept C127413603 @default.
- W3127388429 hasConcept C154945302 @default.
- W3127388429 hasConcept C192209626 @default.
- W3127388429 hasConcept C199360897 @default.
- W3127388429 hasConcept C201995342 @default.
- W3127388429 hasConcept C2780451532 @default.
- W3127388429 hasConcept C2780801425 @default.
- W3127388429 hasConcept C31972630 @default.
- W3127388429 hasConcept C41008148 @default.
- W3127388429 hasConceptScore W3127388429C107457646 @default.
- W3127388429 hasConceptScore W3127388429C119857082 @default.
- W3127388429 hasConceptScore W3127388429C120665830 @default.
- W3127388429 hasConceptScore W3127388429C121332964 @default.
- W3127388429 hasConceptScore W3127388429C127413603 @default.
- W3127388429 hasConceptScore W3127388429C154945302 @default.
- W3127388429 hasConceptScore W3127388429C192209626 @default.
- W3127388429 hasConceptScore W3127388429C199360897 @default.
- W3127388429 hasConceptScore W3127388429C201995342 @default.
- W3127388429 hasConceptScore W3127388429C2780451532 @default.
- W3127388429 hasConceptScore W3127388429C2780801425 @default.
- W3127388429 hasConceptScore W3127388429C31972630 @default.
- W3127388429 hasConceptScore W3127388429C41008148 @default.
- W3127388429 hasLocation W31273884291 @default.
- W3127388429 hasOpenAccess W3127388429 @default.
- W3127388429 hasPrimaryLocation W31273884291 @default.
- W3127388429 hasRelatedWork W2185106784 @default.
- W3127388429 hasRelatedWork W2327781164 @default.
- W3127388429 hasRelatedWork W2777629900 @default.
- W3127388429 hasRelatedWork W2786658125 @default.
- W3127388429 hasRelatedWork W2892590708 @default.
- W3127388429 hasRelatedWork W2951660448 @default.
- W3127388429 hasRelatedWork W2967853831 @default.
- W3127388429 hasRelatedWork W2996508780 @default.
- W3127388429 hasRelatedWork W2998836954 @default.
- W3127388429 hasRelatedWork W3022280754 @default.
- W3127388429 hasRelatedWork W3102804550 @default.
- W3127388429 hasRelatedWork W3111882491 @default.
- W3127388429 hasRelatedWork W3120006980 @default.
- W3127388429 hasRelatedWork W3126672009 @default.
- W3127388429 hasRelatedWork W3176468608 @default.
- W3127388429 hasRelatedWork W3176768792 @default.
- W3127388429 hasRelatedWork W3202783433 @default.
- W3127388429 hasRelatedWork W3207219602 @default.
- W3127388429 hasRelatedWork W3212227062 @default.
- W3127388429 hasRelatedWork W331320916 @default.
- W3127388429 isParatext "false" @default.
- W3127388429 isRetracted "false" @default.
- W3127388429 magId "3127388429" @default.
- W3127388429 workType "article" @default.