Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384918756> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4384918756 abstract "Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In this work, we investigate how to embed and leverage such abilities in Reinforcement Learning (RL) agents. We design a framework that uses language as the core reasoning tool, exploring how this enables an agent to tackle a series of fundamental RL challenges, such as efficient exploration, reusing experience data, scheduling skills, and learning from observations, which traditionally require separate, vertically designed algorithms. We test our method on a sparse-reward simulated robotic manipulation environment, where a robot needs to stack a set of objects. We demonstrate substantial performance improvements over baselines in exploration efficiency and ability to reuse data from offline datasets, and illustrate how to reuse learned skills to solve novel tasks or imitate videos of human experts." @default.
- W4384918756 created "2023-07-21" @default.
- W4384918756 creator A5002747297 @default.
- W4384918756 creator A5014567358 @default.
- W4384918756 creator A5037305533 @default.
- W4384918756 creator A5041323275 @default.
- W4384918756 creator A5062951341 @default.
- W4384918756 creator A5085711106 @default.
- W4384918756 date "2023-07-18" @default.
- W4384918756 modified "2023-09-24" @default.
- W4384918756 title "Towards A Unified Agent with Foundation Models" @default.
- W4384918756 doi "https://doi.org/10.48550/arxiv.2307.09668" @default.
- W4384918756 hasPublicationYear "2023" @default.
- W4384918756 type Work @default.
- W4384918756 citedByCount "0" @default.
- W4384918756 crossrefType "posted-content" @default.
- W4384918756 hasAuthorship W4384918756A5002747297 @default.
- W4384918756 hasAuthorship W4384918756A5014567358 @default.
- W4384918756 hasAuthorship W4384918756A5037305533 @default.
- W4384918756 hasAuthorship W4384918756A5041323275 @default.
- W4384918756 hasAuthorship W4384918756A5062951341 @default.
- W4384918756 hasAuthorship W4384918756A5085711106 @default.
- W4384918756 hasBestOaLocation W43849187561 @default.
- W4384918756 hasConcept C107457646 @default.
- W4384918756 hasConcept C119857082 @default.
- W4384918756 hasConcept C127413603 @default.
- W4384918756 hasConcept C153083717 @default.
- W4384918756 hasConcept C154945302 @default.
- W4384918756 hasConcept C177264268 @default.
- W4384918756 hasConcept C199360897 @default.
- W4384918756 hasConcept C206588197 @default.
- W4384918756 hasConcept C206729178 @default.
- W4384918756 hasConcept C21547014 @default.
- W4384918756 hasConcept C41008148 @default.
- W4384918756 hasConcept C548081761 @default.
- W4384918756 hasConcept C90509273 @default.
- W4384918756 hasConcept C97541855 @default.
- W4384918756 hasConceptScore W4384918756C107457646 @default.
- W4384918756 hasConceptScore W4384918756C119857082 @default.
- W4384918756 hasConceptScore W4384918756C127413603 @default.
- W4384918756 hasConceptScore W4384918756C153083717 @default.
- W4384918756 hasConceptScore W4384918756C154945302 @default.
- W4384918756 hasConceptScore W4384918756C177264268 @default.
- W4384918756 hasConceptScore W4384918756C199360897 @default.
- W4384918756 hasConceptScore W4384918756C206588197 @default.
- W4384918756 hasConceptScore W4384918756C206729178 @default.
- W4384918756 hasConceptScore W4384918756C21547014 @default.
- W4384918756 hasConceptScore W4384918756C41008148 @default.
- W4384918756 hasConceptScore W4384918756C548081761 @default.
- W4384918756 hasConceptScore W4384918756C90509273 @default.
- W4384918756 hasConceptScore W4384918756C97541855 @default.
- W4384918756 hasLocation W43849187561 @default.
- W4384918756 hasOpenAccess W4384918756 @default.
- W4384918756 hasPrimaryLocation W43849187561 @default.
- W4384918756 hasRelatedWork W3022038857 @default.
- W4384918756 hasRelatedWork W3024399153 @default.
- W4384918756 hasRelatedWork W3099427952 @default.
- W4384918756 hasRelatedWork W3170628611 @default.
- W4384918756 hasRelatedWork W3203000071 @default.
- W4384918756 hasRelatedWork W3205824709 @default.
- W4384918756 hasRelatedWork W4252318465 @default.
- W4384918756 hasRelatedWork W4318719223 @default.
- W4384918756 hasRelatedWork W4318719422 @default.
- W4384918756 hasRelatedWork W4319083788 @default.
- W4384918756 isParatext "false" @default.
- W4384918756 isRetracted "false" @default.
- W4384918756 workType "article" @default.