FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962741108> ?p ?o ?g. }

• W2962741108 endingPage "429" @default.
• W2962741108 startingPage "403" @default.
• W2962741108 abstract "In multiagent environments, the capability of learning is important for an agent to behave appropriately in face of unknown opponents and dynamic environment. From the system designer’s perspective, it is desirable if the agents can learn to coordinate towards socially optimal outcomes, while also avoiding being exploited by selfish opponents. To this end, we propose a novel gradient ascent based algorithm (SA-IGA) which augments the basic gradient-ascent algorithm by incorporating social awareness into the policy update process. We theoretically analyze the learning dynamics of SA-IGA using dynamical system theory and SA-IGA is shown to have linear dynamics for a wide range of games including symmetric games. The learning dynamics of two representative games (the prisoner’s dilemma game and the coordination game) are analyzed in detail. Based on the idea of SA-IGA, we further propose a practical multiagent learning algorithm, called SA-PGA, based on Q-learning update rule. Simulation results show that SA-PGA agent can achieve higher social welfare than previous social-optimality oriented Conditional Joint Action Learner (CJAL) and also is robust against individually rational opponents by reaching Nash equilibrium solutions." @default.
• W2962741108 created "2019-07-30" @default.
• W2962741108 creator A5001714538 @default.
• W2962741108 creator A5007940280 @default.
• W2962741108 creator A5008547992 @default.
• W2962741108 creator A5027220635 @default.
• W2962741108 creator A5047509839 @default.
• W2962741108 creator A5083729859 @default.
• W2962741108 creator A5090385327 @default.
• W2962741108 date "2019-05-15" @default.
• W2962741108 modified "2023-10-09" @default.
• W2962741108 title "SA-IGA: a multiagent reinforcement learning method towards socially optimal outcomes" @default.
• W2962741108 cites W1192553058 @default.
• W2962741108 cites W1540725368 @default.
• W2962741108 cites W1542941925 @default.
• W2962741108 cites W1963754118 @default.
• W2962741108 cites W1964408944 @default.
• W2962741108 cites W1967817125 @default.
• W2962741108 cites W2031098375 @default.
• W2962741108 cites W2032703153 @default.
• W2962741108 cites W2065821056 @default.
• W2962741108 cites W2067412374 @default.
• W2962741108 cites W2096145798 @default.
• W2962741108 cites W2099618002 @default.
• W2962741108 cites W2103437045 @default.
• W2962741108 cites W2120327309 @default.
• W2962741108 cites W2124951424 @default.
• W2962741108 cites W2131376880 @default.
• W2962741108 cites W2135649865 @default.
• W2962741108 cites W2338351427 @default.
• W2962741108 cites W2481334653 @default.
• W2962741108 cites W3105048218 @default.
• W2962741108 cites W4292283611 @default.
• W2962741108 doi "https://doi.org/10.1007/s10458-019-09411-3" @default.
• W2962741108 hasPublicationYear "2019" @default.
• W2962741108 type Work @default.
• W2962741108 sameAs 2962741108 @default.
• W2962741108 citedByCount "12" @default.
• W2962741108 countsByYear W29627411082020 @default.
• W2962741108 countsByYear W29627411082021 @default.
• W2962741108 countsByYear W29627411082022 @default.
• W2962741108 countsByYear W29627411082023 @default.
• W2962741108 crossrefType "journal-article" @default.
• W2962741108 hasAuthorship W2962741108A5001714538 @default.
• W2962741108 hasAuthorship W2962741108A5007940280 @default.
• W2962741108 hasAuthorship W2962741108A5008547992 @default.
• W2962741108 hasAuthorship W2962741108A5027220635 @default.
• W2962741108 hasAuthorship W2962741108A5047509839 @default.
• W2962741108 hasAuthorship W2962741108A5083729859 @default.
• W2962741108 hasAuthorship W2962741108A5090385327 @default.
• W2962741108 hasBestOaLocation W29627411082 @default.
• W2962741108 hasConcept C126255220 @default.
• W2962741108 hasConcept C12713177 @default.
• W2962741108 hasConcept C144237770 @default.
• W2962741108 hasConcept C154945302 @default.
• W2962741108 hasConcept C15744967 @default.
• W2962741108 hasConcept C177142836 @default.
• W2962741108 hasConcept C187206662 @default.
• W2962741108 hasConcept C2524010 @default.
• W2962741108 hasConcept C2778496695 @default.
• W2962741108 hasConcept C33923547 @default.
• W2962741108 hasConcept C41008148 @default.
• W2962741108 hasConcept C46814582 @default.
• W2962741108 hasConcept C56739046 @default.
• W2962741108 hasConcept C77805123 @default.
• W2962741108 hasConcept C79416737 @default.
• W2962741108 hasConcept C97541855 @default.
• W2962741108 hasConceptScore W2962741108C126255220 @default.
• W2962741108 hasConceptScore W2962741108C12713177 @default.
• W2962741108 hasConceptScore W2962741108C144237770 @default.
• W2962741108 hasConceptScore W2962741108C154945302 @default.
• W2962741108 hasConceptScore W2962741108C15744967 @default.
• W2962741108 hasConceptScore W2962741108C177142836 @default.
• W2962741108 hasConceptScore W2962741108C187206662 @default.
• W2962741108 hasConceptScore W2962741108C2524010 @default.
• W2962741108 hasConceptScore W2962741108C2778496695 @default.
• W2962741108 hasConceptScore W2962741108C33923547 @default.
• W2962741108 hasConceptScore W2962741108C41008148 @default.
• W2962741108 hasConceptScore W2962741108C46814582 @default.
• W2962741108 hasConceptScore W2962741108C56739046 @default.
• W2962741108 hasConceptScore W2962741108C77805123 @default.
• W2962741108 hasConceptScore W2962741108C79416737 @default.
• W2962741108 hasConceptScore W2962741108C97541855 @default.
• W2962741108 hasFunder F4320321001 @default.
• W2962741108 hasFunder F4320335787 @default.
• W2962741108 hasIssue "4" @default.
• W2962741108 hasLocation W29627411081 @default.
• W2962741108 hasLocation W29627411082 @default.
• W2962741108 hasOpenAccess W2962741108 @default.
• W2962741108 hasPrimaryLocation W29627411081 @default.
• W2962741108 hasRelatedWork W176234586 @default.
• W2962741108 hasRelatedWork W2067015114 @default.
• W2962741108 hasRelatedWork W2145192588 @default.
• W2962741108 hasRelatedWork W2357039837 @default.
• W2962741108 hasRelatedWork W2380527462 @default.
• W2962741108 hasRelatedWork W2888456894 @default.
• W2962741108 hasRelatedWork W2946123577 @default.
• W2962741108 hasRelatedWork W2950219151 @default.

• next