Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999681751> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2999681751 abstract "Robotic agents must adopt existing social conventions in order to be effective teammates. These social conventions, such as driving on the right or left side of the road, are arbitrary choices among optimal policies, but all agents on a successful team must use the same convention. Prior work has identified a method of combining self-play with paired input-output data gathered from existing agents in order to learn their social convention without interacting with them. We build upon this work by introducing a technique called Adversarial Self-Play (ASP) that uses adversarial training to shape the space of possible learned policies and substantially improves learning efficiency. ASP only requires the addition of unpaired data: a dataset of outputs produced by the social convention without associated inputs. Theoretical analysis reveals how ASP shapes the policy space and the circumstances (when behaviors are clustered or exhibit some other structure) under which it offers the greatest benefits. Empirical results across three domains confirm ASP's advantages: it produces models that more closely match the desired social convention when given as few as two paired datapoints." @default.
- W2999681751 created "2020-01-23" @default.
- W2999681751 creator A5044369720 @default.
- W2999681751 creator A5074749353 @default.
- W2999681751 creator A5078421831 @default.
- W2999681751 date "2020-01-16" @default.
- W2999681751 modified "2023-09-23" @default.
- W2999681751 title "Adversarially Guided Self-Play for Adopting Social Conventions." @default.
- W2999681751 cites W1515851193 @default.
- W2999681751 cites W1764574858 @default.
- W2999681751 cites W1997615675 @default.
- W2999681751 cites W2000189111 @default.
- W2999681751 cites W2012378226 @default.
- W2999681751 cites W2085366587 @default.
- W2999681751 cites W2089652186 @default.
- W2999681751 cites W2099471712 @default.
- W2999681751 cites W2110930288 @default.
- W2999681751 cites W2395575420 @default.
- W2999681751 cites W2562637642 @default.
- W2999681751 cites W2564324149 @default.
- W2999681751 cites W2574790321 @default.
- W2999681751 cites W2766447205 @default.
- W2999681751 cites W2777660616 @default.
- W2999681751 cites W28684199 @default.
- W2999681751 cites W2904367110 @default.
- W2999681751 cites W2913781869 @default.
- W2999681751 cites W2951004968 @default.
- W2999681751 cites W2959402823 @default.
- W2999681751 cites W2962793481 @default.
- W2999681751 cites W2963073614 @default.
- W2999681751 cites W2963109634 @default.
- W2999681751 cites W2963407617 @default.
- W2999681751 cites W2963881016 @default.
- W2999681751 cites W2964338167 @default.
- W2999681751 cites W2979363950 @default.
- W2999681751 hasPublicationYear "2020" @default.
- W2999681751 type Work @default.
- W2999681751 sameAs 2999681751 @default.
- W2999681751 citedByCount "4" @default.
- W2999681751 countsByYear W29996817512020 @default.
- W2999681751 countsByYear W29996817512021 @default.
- W2999681751 crossrefType "posted-content" @default.
- W2999681751 hasAuthorship W2999681751A5044369720 @default.
- W2999681751 hasAuthorship W2999681751A5074749353 @default.
- W2999681751 hasAuthorship W2999681751A5078421831 @default.
- W2999681751 hasConcept C10138342 @default.
- W2999681751 hasConcept C111919701 @default.
- W2999681751 hasConcept C127413603 @default.
- W2999681751 hasConcept C144133560 @default.
- W2999681751 hasConcept C154945302 @default.
- W2999681751 hasConcept C17744445 @default.
- W2999681751 hasConcept C182306322 @default.
- W2999681751 hasConcept C18762648 @default.
- W2999681751 hasConcept C199539241 @default.
- W2999681751 hasConcept C2778572836 @default.
- W2999681751 hasConcept C2780608745 @default.
- W2999681751 hasConcept C37736160 @default.
- W2999681751 hasConcept C41008148 @default.
- W2999681751 hasConcept C78519656 @default.
- W2999681751 hasConceptScore W2999681751C10138342 @default.
- W2999681751 hasConceptScore W2999681751C111919701 @default.
- W2999681751 hasConceptScore W2999681751C127413603 @default.
- W2999681751 hasConceptScore W2999681751C144133560 @default.
- W2999681751 hasConceptScore W2999681751C154945302 @default.
- W2999681751 hasConceptScore W2999681751C17744445 @default.
- W2999681751 hasConceptScore W2999681751C182306322 @default.
- W2999681751 hasConceptScore W2999681751C18762648 @default.
- W2999681751 hasConceptScore W2999681751C199539241 @default.
- W2999681751 hasConceptScore W2999681751C2778572836 @default.
- W2999681751 hasConceptScore W2999681751C2780608745 @default.
- W2999681751 hasConceptScore W2999681751C37736160 @default.
- W2999681751 hasConceptScore W2999681751C41008148 @default.
- W2999681751 hasConceptScore W2999681751C78519656 @default.
- W2999681751 hasLocation W29996817511 @default.
- W2999681751 hasOpenAccess W2999681751 @default.
- W2999681751 hasPrimaryLocation W29996817511 @default.
- W2999681751 hasRelatedWork W108336744 @default.
- W2999681751 hasRelatedWork W125707626 @default.
- W2999681751 hasRelatedWork W1538135547 @default.
- W2999681751 hasRelatedWork W164623105 @default.
- W2999681751 hasRelatedWork W2270028217 @default.
- W2999681751 hasRelatedWork W2277732384 @default.
- W2999681751 hasRelatedWork W2400625548 @default.
- W2999681751 hasRelatedWork W2495883354 @default.
- W2999681751 hasRelatedWork W2576346312 @default.
- W2999681751 hasRelatedWork W2790671784 @default.
- W2999681751 hasRelatedWork W2810298113 @default.
- W2999681751 hasRelatedWork W2891471758 @default.
- W2999681751 hasRelatedWork W2892364115 @default.
- W2999681751 hasRelatedWork W2950584629 @default.
- W2999681751 hasRelatedWork W2964436503 @default.
- W2999681751 hasRelatedWork W2982654372 @default.
- W2999681751 hasRelatedWork W2996465135 @default.
- W2999681751 hasRelatedWork W3039416122 @default.
- W2999681751 hasRelatedWork W631965503 @default.
- W2999681751 hasRelatedWork W9516865 @default.
- W2999681751 isParatext "false" @default.
- W2999681751 isRetracted "false" @default.
- W2999681751 magId "2999681751" @default.
- W2999681751 workType "article" @default.