Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309584580> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4309584580 abstract "Embodied AI agents continue to become more capable every year with the advent of new models, environments, and benchmarks, but are still far away from being performant and reliable enough to be deployed in real, user-facing, applications. In this paper, we ask: can we bridge this gap by enabling agents to ask for assistance from an expert such as a human being? To this end, we propose the Ask4Help policy that augments agents with the ability to request, and then use expert assistance. Ask4Help policies can be efficiently trained without modifying the original agent's parameters and learn a desirable trade-off between task performance and the amount of requested help, thereby reducing the cost of querying the expert. We evaluate Ask4Help on two different tasks -- object goal navigation and room rearrangement and see substantial improvements in performance using minimal help. On object navigation, an agent that achieves a $52%$ success rate is raised to $86%$ with $13%$ help and for rearrangement, the state-of-the-art model with a $7%$ success rate is dramatically improved to $90.4%$ using $39%$ help. Human trials with Ask4Help demonstrate the efficacy of our approach in practical scenarios. We release the code for Ask4Help here: https://github.com/allenai/ask4help." @default.
- W4309584580 created "2022-11-28" @default.
- W4309584580 creator A5034116241 @default.
- W4309584580 creator A5045298700 @default.
- W4309584580 creator A5045695842 @default.
- W4309584580 creator A5057329354 @default.
- W4309584580 creator A5070375939 @default.
- W4309584580 creator A5073483751 @default.
- W4309584580 date "2022-11-17" @default.
- W4309584580 modified "2023-10-01" @default.
- W4309584580 title "Ask4Help: Learning to Leverage an Expert for Embodied Tasks" @default.
- W4309584580 doi "https://doi.org/10.48550/arxiv.2211.09960" @default.
- W4309584580 hasPublicationYear "2022" @default.
- W4309584580 type Work @default.
- W4309584580 citedByCount "0" @default.
- W4309584580 crossrefType "posted-content" @default.
- W4309584580 hasAuthorship W4309584580A5034116241 @default.
- W4309584580 hasAuthorship W4309584580A5045298700 @default.
- W4309584580 hasAuthorship W4309584580A5045695842 @default.
- W4309584580 hasAuthorship W4309584580A5057329354 @default.
- W4309584580 hasAuthorship W4309584580A5070375939 @default.
- W4309584580 hasAuthorship W4309584580A5073483751 @default.
- W4309584580 hasBestOaLocation W43095845801 @default.
- W4309584580 hasConcept C100609095 @default.
- W4309584580 hasConcept C100776233 @default.
- W4309584580 hasConcept C107457646 @default.
- W4309584580 hasConcept C126322002 @default.
- W4309584580 hasConcept C127413603 @default.
- W4309584580 hasConcept C136264566 @default.
- W4309584580 hasConcept C153083717 @default.
- W4309584580 hasConcept C154945302 @default.
- W4309584580 hasConcept C162324750 @default.
- W4309584580 hasConcept C201995342 @default.
- W4309584580 hasConcept C2780451532 @default.
- W4309584580 hasConcept C41008148 @default.
- W4309584580 hasConcept C71924100 @default.
- W4309584580 hasConcept C90329073 @default.
- W4309584580 hasConceptScore W4309584580C100609095 @default.
- W4309584580 hasConceptScore W4309584580C100776233 @default.
- W4309584580 hasConceptScore W4309584580C107457646 @default.
- W4309584580 hasConceptScore W4309584580C126322002 @default.
- W4309584580 hasConceptScore W4309584580C127413603 @default.
- W4309584580 hasConceptScore W4309584580C136264566 @default.
- W4309584580 hasConceptScore W4309584580C153083717 @default.
- W4309584580 hasConceptScore W4309584580C154945302 @default.
- W4309584580 hasConceptScore W4309584580C162324750 @default.
- W4309584580 hasConceptScore W4309584580C201995342 @default.
- W4309584580 hasConceptScore W4309584580C2780451532 @default.
- W4309584580 hasConceptScore W4309584580C41008148 @default.
- W4309584580 hasConceptScore W4309584580C71924100 @default.
- W4309584580 hasConceptScore W4309584580C90329073 @default.
- W4309584580 hasLocation W43095845801 @default.
- W4309584580 hasOpenAccess W4309584580 @default.
- W4309584580 hasPrimaryLocation W43095845801 @default.
- W4309584580 hasRelatedWork W2031296774 @default.
- W4309584580 hasRelatedWork W2081647779 @default.
- W4309584580 hasRelatedWork W2325123304 @default.
- W4309584580 hasRelatedWork W2506896584 @default.
- W4309584580 hasRelatedWork W3036497058 @default.
- W4309584580 hasRelatedWork W4283369588 @default.
- W4309584580 hasRelatedWork W4303647895 @default.
- W4309584580 hasRelatedWork W4320343045 @default.
- W4309584580 hasRelatedWork W4327926809 @default.
- W4309584580 hasRelatedWork W4385656309 @default.
- W4309584580 isParatext "false" @default.
- W4309584580 isRetracted "false" @default.
- W4309584580 workType "article" @default.