Matches in SemOpenAlex for { <https://semopenalex.org/work/W3116313901> ?p ?o ?g. }
- W3116313901 abstract "We consider a multi-agent Markov strategic interaction over an infinite horizon where agents can be of multiple types. We model the strategic interaction as a mean-field game in the asymptotic limit when the number of agents of each type becomes infinite. Each agent has a private state; the state evolves depending on the distribution of the state of the agents of different types and the action of the agent. Each agent wants to maximize the discounted sum of rewards over the infinite horizon which depends on the state of the agent and the distribution of the state of the leaders and followers. We seek to characterize and compute a stationary multi-type Mean field equilibrium (MMFE) in the above game. We characterize the conditions under which a stationary MMFE exists. Finally, we propose Reinforcement learning (RL) based algorithm using policy gradient approach to find the stationary MMFE when the agents are unaware of the dynamics. We, numerically, evaluate how such kind of interaction can model the cyber attacks among defenders and adversaries, and show how RL based algorithm can converge to an equilibrium." @default.
- W3116313901 created "2021-01-05" @default.
- W3116313901 creator A5022713299 @default.
- W3116313901 creator A5064822688 @default.
- W3116313901 date "2020-12-31" @default.
- W3116313901 modified "2023-09-26" @default.
- W3116313901 title "Model Free Reinforcement Learning Algorithm for Stationary Mean field Equilibrium for Multiple Types of Agents." @default.
- W3116313901 cites W1513468570 @default.
- W3116313901 cites W1542941925 @default.
- W3116313901 cites W1641379095 @default.
- W3116313901 cites W2011000015 @default.
- W3116313901 cites W2029804570 @default.
- W3116313901 cites W206679605 @default.
- W3116313901 cites W2075475763 @default.
- W3116313901 cites W2089994460 @default.
- W3116313901 cites W2132241089 @default.
- W3116313901 cites W2161949749 @default.
- W3116313901 cites W2212130646 @default.
- W3116313901 cites W2788807191 @default.
- W3116313901 cites W2799002770 @default.
- W3116313901 cites W2902676408 @default.
- W3116313901 cites W2945395894 @default.
- W3116313901 cites W2951915386 @default.
- W3116313901 cites W2963039558 @default.
- W3116313901 cites W2970875146 @default.
- W3116313901 cites W2979330446 @default.
- W3116313901 cites W2980452497 @default.
- W3116313901 cites W2981038142 @default.
- W3116313901 cites W2982138249 @default.
- W3116313901 cites W2997056010 @default.
- W3116313901 cites W3011617603 @default.
- W3116313901 cites W3044834640 @default.
- W3116313901 cites W3099043603 @default.
- W3116313901 cites W3118479214 @default.
- W3116313901 cites W3161773474 @default.
- W3116313901 hasPublicationYear "2020" @default.
- W3116313901 type Work @default.
- W3116313901 sameAs 3116313901 @default.
- W3116313901 citedByCount "1" @default.
- W3116313901 countsByYear W31163139012021 @default.
- W3116313901 crossrefType "posted-content" @default.
- W3116313901 hasAuthorship W3116313901A5022713299 @default.
- W3116313901 hasAuthorship W3116313901A5064822688 @default.
- W3116313901 hasConcept C105795698 @default.
- W3116313901 hasConcept C106189395 @default.
- W3116313901 hasConcept C110121322 @default.
- W3116313901 hasConcept C11413529 @default.
- W3116313901 hasConcept C119857082 @default.
- W3116313901 hasConcept C121332964 @default.
- W3116313901 hasConcept C126255220 @default.
- W3116313901 hasConcept C134306372 @default.
- W3116313901 hasConcept C144237770 @default.
- W3116313901 hasConcept C145071142 @default.
- W3116313901 hasConcept C151201525 @default.
- W3116313901 hasConcept C154945302 @default.
- W3116313901 hasConcept C159176650 @default.
- W3116313901 hasConcept C159886148 @default.
- W3116313901 hasConcept C188116033 @default.
- W3116313901 hasConcept C18903297 @default.
- W3116313901 hasConcept C202444582 @default.
- W3116313901 hasConcept C2524010 @default.
- W3116313901 hasConcept C2777299769 @default.
- W3116313901 hasConcept C28761237 @default.
- W3116313901 hasConcept C33923547 @default.
- W3116313901 hasConcept C41008148 @default.
- W3116313901 hasConcept C46814582 @default.
- W3116313901 hasConcept C47458137 @default.
- W3116313901 hasConcept C48103436 @default.
- W3116313901 hasConcept C62520636 @default.
- W3116313901 hasConcept C67091656 @default.
- W3116313901 hasConcept C86803240 @default.
- W3116313901 hasConcept C9652623 @default.
- W3116313901 hasConcept C97541855 @default.
- W3116313901 hasConcept C98763669 @default.
- W3116313901 hasConcept C98951983 @default.
- W3116313901 hasConceptScore W3116313901C105795698 @default.
- W3116313901 hasConceptScore W3116313901C106189395 @default.
- W3116313901 hasConceptScore W3116313901C110121322 @default.
- W3116313901 hasConceptScore W3116313901C11413529 @default.
- W3116313901 hasConceptScore W3116313901C119857082 @default.
- W3116313901 hasConceptScore W3116313901C121332964 @default.
- W3116313901 hasConceptScore W3116313901C126255220 @default.
- W3116313901 hasConceptScore W3116313901C134306372 @default.
- W3116313901 hasConceptScore W3116313901C144237770 @default.
- W3116313901 hasConceptScore W3116313901C145071142 @default.
- W3116313901 hasConceptScore W3116313901C151201525 @default.
- W3116313901 hasConceptScore W3116313901C154945302 @default.
- W3116313901 hasConceptScore W3116313901C159176650 @default.
- W3116313901 hasConceptScore W3116313901C159886148 @default.
- W3116313901 hasConceptScore W3116313901C188116033 @default.
- W3116313901 hasConceptScore W3116313901C18903297 @default.
- W3116313901 hasConceptScore W3116313901C202444582 @default.
- W3116313901 hasConceptScore W3116313901C2524010 @default.
- W3116313901 hasConceptScore W3116313901C2777299769 @default.
- W3116313901 hasConceptScore W3116313901C28761237 @default.
- W3116313901 hasConceptScore W3116313901C33923547 @default.
- W3116313901 hasConceptScore W3116313901C41008148 @default.
- W3116313901 hasConceptScore W3116313901C46814582 @default.
- W3116313901 hasConceptScore W3116313901C47458137 @default.
- W3116313901 hasConceptScore W3116313901C48103436 @default.