SemOpenAlex |

SemOpenAlex

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100614249> ?p ?o ?g. }

Showing items 1 to 81 of 81 with 100 items per page.

W3100614249 endingPage "15799" @default.
W3100614249 startingPage "15786" @default.
W3100614249 abstract "Multi-agent reinforcement learning (MARL) has shown recent success in increasingly complex fixed-team zero-sum environments. However, the real world is not zero-sum nor does it have fixed teams; humans face numerous social dilemmas and must learn when to cooperate and when to compete. To successfully deploy agents into the human world, it may be important that they be able to understand and help in our conflicts. Unfortunately, selfish MARL agents typically fail when faced with social dilemmas. In this work, we show evidence of emergent direct reciprocity, indirect reciprocity and reputation, and team formation when training agents with randomized uncertain social preferences (RUSP), a novel environment augmentation that expands the distribution of environments agents play in. RUSP is generic and scalable; it can be applied to any multi-agent environment without changing the original underlying game dynamics or objectives. In particular, we show that with RUSP these behaviors can emerge and lead to higher social welfare equilibria in both classic abstract social dilemmas like Iterated Prisoner's Dilemma as well in more complex intertemporal environments." @default.
W3100614249 created "2020-11-23" @default.
W3100614249 creator A5048522044 @default.
W3100614249 date "2020-01-01" @default.
W3100614249 modified "2023-09-24" @default.
W3100614249 title "Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences" @default.
W3100614249 hasPublicationYear "2020" @default.
W3100614249 type Work @default.
W3100614249 sameAs 3100614249 @default.
W3100614249 citedByCount "1" @default.
W3100614249 countsByYear W31006142492020 @default.
W3100614249 crossrefType "proceedings-article" @default.
W3100614249 hasAuthorship W3100614249A5048522044 @default.
W3100614249 hasConcept C111472728 @default.
W3100614249 hasConcept C113494165 @default.
W3100614249 hasConcept C138885662 @default.
W3100614249 hasConcept C154945302 @default.
W3100614249 hasConcept C15744967 @default.
W3100614249 hasConcept C162324750 @default.
W3100614249 hasConcept C169903001 @default.
W3100614249 hasConcept C175444787 @default.
W3100614249 hasConcept C177142836 @default.
W3100614249 hasConcept C17744445 @default.
W3100614249 hasConcept C187206662 @default.
W3100614249 hasConcept C199539241 @default.
W3100614249 hasConcept C2778496695 @default.
W3100614249 hasConcept C41008148 @default.
W3100614249 hasConcept C48798503 @default.
W3100614249 hasConcept C56739046 @default.
W3100614249 hasConcept C77805123 @default.
W3100614249 hasConcept C79416737 @default.
W3100614249 hasConcept C97541855 @default.
W3100614249 hasConceptScore W3100614249C111472728 @default.
W3100614249 hasConceptScore W3100614249C113494165 @default.
W3100614249 hasConceptScore W3100614249C138885662 @default.
W3100614249 hasConceptScore W3100614249C154945302 @default.
W3100614249 hasConceptScore W3100614249C15744967 @default.
W3100614249 hasConceptScore W3100614249C162324750 @default.
W3100614249 hasConceptScore W3100614249C169903001 @default.
W3100614249 hasConceptScore W3100614249C175444787 @default.
W3100614249 hasConceptScore W3100614249C177142836 @default.
W3100614249 hasConceptScore W3100614249C17744445 @default.
W3100614249 hasConceptScore W3100614249C187206662 @default.
W3100614249 hasConceptScore W3100614249C199539241 @default.
W3100614249 hasConceptScore W3100614249C2778496695 @default.
W3100614249 hasConceptScore W3100614249C41008148 @default.
W3100614249 hasConceptScore W3100614249C48798503 @default.
W3100614249 hasConceptScore W3100614249C56739046 @default.
W3100614249 hasConceptScore W3100614249C77805123 @default.
W3100614249 hasConceptScore W3100614249C79416737 @default.
W3100614249 hasConceptScore W3100614249C97541855 @default.
W3100614249 hasLocation W31006142491 @default.
W3100614249 hasOpenAccess W3100614249 @default.
W3100614249 hasPrimaryLocation W31006142491 @default.
W3100614249 hasRelatedWork W186156470 @default.
W3100614249 hasRelatedWork W2155986772 @default.
W3100614249 hasRelatedWork W2328942586 @default.
W3100614249 hasRelatedWork W2382569642 @default.
W3100614249 hasRelatedWork W2594794854 @default.
W3100614249 hasRelatedWork W2730328371 @default.
W3100614249 hasRelatedWork W2766328909 @default.
W3100614249 hasRelatedWork W2793234362 @default.
W3100614249 hasRelatedWork W2811498230 @default.
W3100614249 hasRelatedWork W2891661335 @default.
W3100614249 hasRelatedWork W2909308108 @default.
W3100614249 hasRelatedWork W2946657772 @default.
W3100614249 hasRelatedWork W2999329929 @default.
W3100614249 hasRelatedWork W3005802885 @default.
W3100614249 hasRelatedWork W3030918235 @default.
W3100614249 hasRelatedWork W3098194351 @default.
W3100614249 hasRelatedWork W3106533735 @default.
W3100614249 hasRelatedWork W3140883334 @default.
W3100614249 hasRelatedWork W3158207331 @default.
W3100614249 hasRelatedWork W3212652405 @default.
W3100614249 hasVolume "33" @default.
W3100614249 isParatext "false" @default.
W3100614249 isRetracted "false" @default.
W3100614249 magId "3100614249" @default.
W3100614249 workType "article" @default.