Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223442942> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4223442942 abstract "A major challenge in multi-agent systems is that the system complexity grows dramatically with the number of agents as well as the size of their action spaces, which is typical in real world scenarios such as autonomous vehicles, robotic teams, network routing, etc. It is hence in imminent need to design decentralized or independent algorithms where the update of each agent is only based on their local observations without the need of introducing complex communication/coordination mechanisms. In this work, we study the finite-time convergence of independent entropy-regularized natural policy gradient (NPG) methods for potential games, where the difference in an agent's utility function due to unilateral deviation matches exactly that of a common potential function. The proposed entropy-regularized NPG method enables each agent to deploy symmetric, decentralized, and multiplicative updates according to its own payoff. We show that the proposed method converges to the quantal response equilibrium (QRE) -- the equilibrium to the entropy-regularized game -- at a sublinear rate, which is independent of the size of the action space and grows at most sublinearly with the number of agents. Appealingly, the convergence rate further becomes independent with the number of agents for the important special case of identical-interest games, leading to the first method that converges at a dimension-free rate. Our approach can be used as a smoothing technique to find an approximate Nash equilibrium (NE) of the unregularized problem without assuming that stationary policies are isolated." @default.
- W4223442942 created "2022-04-14" @default.
- W4223442942 creator A5003322678 @default.
- W4223442942 creator A5053809095 @default.
- W4223442942 creator A5091389636 @default.
- W4223442942 date "2022-04-11" @default.
- W4223442942 modified "2023-10-18" @default.
- W4223442942 title "Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization" @default.
- W4223442942 doi "https://doi.org/10.48550/arxiv.2204.05466" @default.
- W4223442942 hasPublicationYear "2022" @default.
- W4223442942 type Work @default.
- W4223442942 citedByCount "0" @default.
- W4223442942 crossrefType "posted-content" @default.
- W4223442942 hasAuthorship W4223442942A5003322678 @default.
- W4223442942 hasAuthorship W4223442942A5053809095 @default.
- W4223442942 hasAuthorship W4223442942A5091389636 @default.
- W4223442942 hasBestOaLocation W42234429421 @default.
- W4223442942 hasConcept C106301342 @default.
- W4223442942 hasConcept C117160843 @default.
- W4223442942 hasConcept C118615104 @default.
- W4223442942 hasConcept C121332964 @default.
- W4223442942 hasConcept C126255220 @default.
- W4223442942 hasConcept C127162648 @default.
- W4223442942 hasConcept C134306372 @default.
- W4223442942 hasConcept C144237770 @default.
- W4223442942 hasConcept C154945302 @default.
- W4223442942 hasConcept C22171661 @default.
- W4223442942 hasConcept C2776135515 @default.
- W4223442942 hasConcept C2778079155 @default.
- W4223442942 hasConcept C28826006 @default.
- W4223442942 hasConcept C31258907 @default.
- W4223442942 hasConcept C31972630 @default.
- W4223442942 hasConcept C32407928 @default.
- W4223442942 hasConcept C33923547 @default.
- W4223442942 hasConcept C3770464 @default.
- W4223442942 hasConcept C41008148 @default.
- W4223442942 hasConcept C42747912 @default.
- W4223442942 hasConcept C46814582 @default.
- W4223442942 hasConcept C57869625 @default.
- W4223442942 hasConcept C62520636 @default.
- W4223442942 hasConceptScore W4223442942C106301342 @default.
- W4223442942 hasConceptScore W4223442942C117160843 @default.
- W4223442942 hasConceptScore W4223442942C118615104 @default.
- W4223442942 hasConceptScore W4223442942C121332964 @default.
- W4223442942 hasConceptScore W4223442942C126255220 @default.
- W4223442942 hasConceptScore W4223442942C127162648 @default.
- W4223442942 hasConceptScore W4223442942C134306372 @default.
- W4223442942 hasConceptScore W4223442942C144237770 @default.
- W4223442942 hasConceptScore W4223442942C154945302 @default.
- W4223442942 hasConceptScore W4223442942C22171661 @default.
- W4223442942 hasConceptScore W4223442942C2776135515 @default.
- W4223442942 hasConceptScore W4223442942C2778079155 @default.
- W4223442942 hasConceptScore W4223442942C28826006 @default.
- W4223442942 hasConceptScore W4223442942C31258907 @default.
- W4223442942 hasConceptScore W4223442942C31972630 @default.
- W4223442942 hasConceptScore W4223442942C32407928 @default.
- W4223442942 hasConceptScore W4223442942C33923547 @default.
- W4223442942 hasConceptScore W4223442942C3770464 @default.
- W4223442942 hasConceptScore W4223442942C41008148 @default.
- W4223442942 hasConceptScore W4223442942C42747912 @default.
- W4223442942 hasConceptScore W4223442942C46814582 @default.
- W4223442942 hasConceptScore W4223442942C57869625 @default.
- W4223442942 hasConceptScore W4223442942C62520636 @default.
- W4223442942 hasLocation W42234429421 @default.
- W4223442942 hasOpenAccess W4223442942 @default.
- W4223442942 hasPrimaryLocation W42234429421 @default.
- W4223442942 hasRelatedWork W1976751517 @default.
- W4223442942 hasRelatedWork W2030158111 @default.
- W4223442942 hasRelatedWork W2103014597 @default.
- W4223442942 hasRelatedWork W2558486865 @default.
- W4223442942 hasRelatedWork W2605224496 @default.
- W4223442942 hasRelatedWork W2889377357 @default.
- W4223442942 hasRelatedWork W2967850360 @default.
- W4223442942 hasRelatedWork W4223442942 @default.
- W4223442942 hasRelatedWork W4224313047 @default.
- W4223442942 hasRelatedWork W4297437344 @default.
- W4223442942 isParatext "false" @default.
- W4223442942 isRetracted "false" @default.
- W4223442942 workType "article" @default.