Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367000507> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4367000507 abstract "Recent research in multi-agent reinforcement learning (MARL) has shown success in learning social behavior and cooperation. Social dilemmas between agents in mixed-sum settings have been studied extensively, but there is little research into social dilemmas in fullycooperative settings, where agents have no prospect of gaining reward at another agent's expense. While fully-aligned interests are conducive to cooperation between agents, they do not guarantee it. We propose a measure of stubbornness between agents that aims to capture the human social behavior from which it takes its name: a disagreement that is gradually escalating and potentially disastrous. We would like to promote research into the tendency of agents to be stubborn, the reactions of counterpart agents, and the resulting social dynamics. In this paper we present Stubborn, an environment for evaluating stubbornness between agents with fully-aligned incentives. In our preliminary results, the agents learn to use their partner's stubbornness as a signal for improving the choices that they make in the environment." @default.
- W4367000507 created "2023-04-27" @default.
- W4367000507 creator A5028581334 @default.
- W4367000507 creator A5036081979 @default.
- W4367000507 creator A5083920910 @default.
- W4367000507 date "2023-04-24" @default.
- W4367000507 modified "2023-10-01" @default.
- W4367000507 title "Stubborn: An Environment for Evaluating Stubbornness between Agents with Aligned Incentives" @default.
- W4367000507 doi "https://doi.org/10.48550/arxiv.2304.12280" @default.
- W4367000507 hasPublicationYear "2023" @default.
- W4367000507 type Work @default.
- W4367000507 citedByCount "0" @default.
- W4367000507 crossrefType "posted-content" @default.
- W4367000507 hasAuthorship W4367000507A5028581334 @default.
- W4367000507 hasAuthorship W4367000507A5036081979 @default.
- W4367000507 hasAuthorship W4367000507A5083920910 @default.
- W4367000507 hasBestOaLocation W43670005071 @default.
- W4367000507 hasConcept C154945302 @default.
- W4367000507 hasConcept C15744967 @default.
- W4367000507 hasConcept C162324750 @default.
- W4367000507 hasConcept C175444787 @default.
- W4367000507 hasConcept C187206662 @default.
- W4367000507 hasConcept C29122968 @default.
- W4367000507 hasConcept C41008148 @default.
- W4367000507 hasConcept C56739046 @default.
- W4367000507 hasConcept C77805123 @default.
- W4367000507 hasConcept C79416737 @default.
- W4367000507 hasConcept C97541855 @default.
- W4367000507 hasConceptScore W4367000507C154945302 @default.
- W4367000507 hasConceptScore W4367000507C15744967 @default.
- W4367000507 hasConceptScore W4367000507C162324750 @default.
- W4367000507 hasConceptScore W4367000507C175444787 @default.
- W4367000507 hasConceptScore W4367000507C187206662 @default.
- W4367000507 hasConceptScore W4367000507C29122968 @default.
- W4367000507 hasConceptScore W4367000507C41008148 @default.
- W4367000507 hasConceptScore W4367000507C56739046 @default.
- W4367000507 hasConceptScore W4367000507C77805123 @default.
- W4367000507 hasConceptScore W4367000507C79416737 @default.
- W4367000507 hasConceptScore W4367000507C97541855 @default.
- W4367000507 hasLocation W43670005071 @default.
- W4367000507 hasOpenAccess W4367000507 @default.
- W4367000507 hasPrimaryLocation W43670005071 @default.
- W4367000507 hasRelatedWork W2155986772 @default.
- W4367000507 hasRelatedWork W2748952813 @default.
- W4367000507 hasRelatedWork W2768777447 @default.
- W4367000507 hasRelatedWork W2893188946 @default.
- W4367000507 hasRelatedWork W2899084033 @default.
- W4367000507 hasRelatedWork W2946123577 @default.
- W4367000507 hasRelatedWork W2948042292 @default.
- W4367000507 hasRelatedWork W2951146095 @default.
- W4367000507 hasRelatedWork W3047256514 @default.
- W4367000507 hasRelatedWork W3162956540 @default.
- W4367000507 isParatext "false" @default.
- W4367000507 isRetracted "false" @default.
- W4367000507 workType "article" @default.