Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288055820> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4288055820 abstract "Multi-goal policy learning for robotic manipulation is challenging. Prior successes have used state-based representations of the objects or provided demonstration data to facilitate learning. In this paper, by hand-coding a high-level discrete representation of the domain, we show that policies to reach dozens of goals can be learned with a single network using Q-learning from pixels. The agent focuses learning on simpler, local policies which are sequenced together by planning in the abstract space. We compare our method against standard multi-goal RL baselines, as well as other methods that leverage the discrete representation, on a challenging block construction domain. We find that our method can build more than a hundred different block structures, and demonstrate forward transfer to structures with novel objects. Lastly, we deploy the policy learned in simulation on a real robot." @default.
- W4288055820 created "2022-07-28" @default.
- W4288055820 creator A5050593664 @default.
- W4288055820 creator A5060590650 @default.
- W4288055820 creator A5072578581 @default.
- W4288055820 date "2022-07-22" @default.
- W4288055820 modified "2023-10-18" @default.
- W4288055820 title "Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks" @default.
- W4288055820 doi "https://doi.org/10.48550/arxiv.2207.11313" @default.
- W4288055820 hasPublicationYear "2022" @default.
- W4288055820 type Work @default.
- W4288055820 citedByCount "0" @default.
- W4288055820 crossrefType "posted-content" @default.
- W4288055820 hasAuthorship W4288055820A5050593664 @default.
- W4288055820 hasAuthorship W4288055820A5060590650 @default.
- W4288055820 hasAuthorship W4288055820A5072578581 @default.
- W4288055820 hasBestOaLocation W42880558201 @default.
- W4288055820 hasConcept C105795698 @default.
- W4288055820 hasConcept C119857082 @default.
- W4288055820 hasConcept C132525143 @default.
- W4288055820 hasConcept C134306372 @default.
- W4288055820 hasConcept C150899416 @default.
- W4288055820 hasConcept C153083717 @default.
- W4288055820 hasConcept C154945302 @default.
- W4288055820 hasConcept C17744445 @default.
- W4288055820 hasConcept C179518139 @default.
- W4288055820 hasConcept C199539241 @default.
- W4288055820 hasConcept C2524010 @default.
- W4288055820 hasConcept C2776359362 @default.
- W4288055820 hasConcept C2777210771 @default.
- W4288055820 hasConcept C2779436431 @default.
- W4288055820 hasConcept C33923547 @default.
- W4288055820 hasConcept C36503486 @default.
- W4288055820 hasConcept C41008148 @default.
- W4288055820 hasConcept C59404180 @default.
- W4288055820 hasConcept C80444323 @default.
- W4288055820 hasConcept C90509273 @default.
- W4288055820 hasConcept C94625758 @default.
- W4288055820 hasConcept C97541855 @default.
- W4288055820 hasConceptScore W4288055820C105795698 @default.
- W4288055820 hasConceptScore W4288055820C119857082 @default.
- W4288055820 hasConceptScore W4288055820C132525143 @default.
- W4288055820 hasConceptScore W4288055820C134306372 @default.
- W4288055820 hasConceptScore W4288055820C150899416 @default.
- W4288055820 hasConceptScore W4288055820C153083717 @default.
- W4288055820 hasConceptScore W4288055820C154945302 @default.
- W4288055820 hasConceptScore W4288055820C17744445 @default.
- W4288055820 hasConceptScore W4288055820C179518139 @default.
- W4288055820 hasConceptScore W4288055820C199539241 @default.
- W4288055820 hasConceptScore W4288055820C2524010 @default.
- W4288055820 hasConceptScore W4288055820C2776359362 @default.
- W4288055820 hasConceptScore W4288055820C2777210771 @default.
- W4288055820 hasConceptScore W4288055820C2779436431 @default.
- W4288055820 hasConceptScore W4288055820C33923547 @default.
- W4288055820 hasConceptScore W4288055820C36503486 @default.
- W4288055820 hasConceptScore W4288055820C41008148 @default.
- W4288055820 hasConceptScore W4288055820C59404180 @default.
- W4288055820 hasConceptScore W4288055820C80444323 @default.
- W4288055820 hasConceptScore W4288055820C90509273 @default.
- W4288055820 hasConceptScore W4288055820C94625758 @default.
- W4288055820 hasConceptScore W4288055820C97541855 @default.
- W4288055820 hasLocation W42880558201 @default.
- W4288055820 hasOpenAccess W4288055820 @default.
- W4288055820 hasPrimaryLocation W42880558201 @default.
- W4288055820 hasRelatedWork W10852009 @default.
- W4288055820 hasRelatedWork W10944326 @default.
- W4288055820 hasRelatedWork W11104910 @default.
- W4288055820 hasRelatedWork W4806451 @default.
- W4288055820 hasRelatedWork W5081013 @default.
- W4288055820 hasRelatedWork W7084024 @default.
- W4288055820 hasRelatedWork W7303821 @default.
- W4288055820 hasRelatedWork W868042 @default.
- W4288055820 hasRelatedWork W8794964 @default.
- W4288055820 hasRelatedWork W929682 @default.
- W4288055820 isParatext "false" @default.
- W4288055820 isRetracted "false" @default.
- W4288055820 workType "article" @default.