Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964059631> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2964059631 abstract "Multiagent systems where agents interact among themselves and with a stochastic environment can be formalized as stochastic games. We study a subclass named Markov potential games (MPGs) that appear often in economic and engineering applications when the agents share a common resource. We consider MPGs with continuous state-action variables, coupled constraints and nonconvex rewards. Previous analysis followed a variational approach that is only valid for very simple cases (convex rewards, invertible dynamics, and no coupled constraints); or considered deterministic dynamics and provided open-loop (OL) analysis, studying strategies that consist in predefined action sequences, which are not optimal for stochastic environments. We present a closed-loop (CL) analysis for MPGs and consider parametric policies that depend on the current state. We provide easily verifiable, sufficient and necessary conditions for a stochastic game to be an MPG, even for complex parametric functions (e.g., deep neural networks); and show that a closed-loop Nash equilibrium (NE) can be found (or at least approximated) by solving a related optimal control problem (OCP). This is useful since solving an OCP--which is a single-objective problem--is usually much simpler than solving the original set of coupled OCPs that form the game--which is a multiobjective control problem. This is a considerable improvement over the previously standard approach for the CL analysis of MPGs, which gives no approximate solution if no NE belongs to the chosen parametric family, and which is practical only for simple parametric forms. We illustrate the theoretical contributions with an example by applying our approach to a noncooperative communications engineering game. We then solve the game with a deep reinforcement learning algorithm that learns policies that closely approximates an exact variational NE of the game." @default.
- W2964059631 created "2019-07-30" @default.
- W2964059631 creator A5008317106 @default.
- W2964059631 creator A5020455236 @default.
- W2964059631 creator A5031787043 @default.
- W2964059631 date "2018-02-15" @default.
- W2964059631 modified "2023-10-01" @default.
- W2964059631 title "Learning Parametric Closed-Loop Policies for Markov Potential Games" @default.
- W2964059631 hasPublicationYear "2018" @default.
- W2964059631 type Work @default.
- W2964059631 sameAs 2964059631 @default.
- W2964059631 citedByCount "3" @default.
- W2964059631 countsByYear W29640596312020 @default.
- W2964059631 countsByYear W29640596312021 @default.
- W2964059631 crossrefType "proceedings-article" @default.
- W2964059631 hasAuthorship W2964059631A5008317106 @default.
- W2964059631 hasAuthorship W2964059631A5020455236 @default.
- W2964059631 hasAuthorship W2964059631A5031787043 @default.
- W2964059631 hasConcept C105795698 @default.
- W2964059631 hasConcept C106189395 @default.
- W2964059631 hasConcept C111472728 @default.
- W2964059631 hasConcept C117251300 @default.
- W2964059631 hasConcept C119857082 @default.
- W2964059631 hasConcept C126255220 @default.
- W2964059631 hasConcept C138885662 @default.
- W2964059631 hasConcept C159886148 @default.
- W2964059631 hasConcept C2780586882 @default.
- W2964059631 hasConcept C33923547 @default.
- W2964059631 hasConcept C41008148 @default.
- W2964059631 hasConcept C46814582 @default.
- W2964059631 hasConcept C98763669 @default.
- W2964059631 hasConceptScore W2964059631C105795698 @default.
- W2964059631 hasConceptScore W2964059631C106189395 @default.
- W2964059631 hasConceptScore W2964059631C111472728 @default.
- W2964059631 hasConceptScore W2964059631C117251300 @default.
- W2964059631 hasConceptScore W2964059631C119857082 @default.
- W2964059631 hasConceptScore W2964059631C126255220 @default.
- W2964059631 hasConceptScore W2964059631C138885662 @default.
- W2964059631 hasConceptScore W2964059631C159886148 @default.
- W2964059631 hasConceptScore W2964059631C2780586882 @default.
- W2964059631 hasConceptScore W2964059631C33923547 @default.
- W2964059631 hasConceptScore W2964059631C41008148 @default.
- W2964059631 hasConceptScore W2964059631C46814582 @default.
- W2964059631 hasConceptScore W2964059631C98763669 @default.
- W2964059631 hasLocation W29640596311 @default.
- W2964059631 hasOpenAccess W2964059631 @default.
- W2964059631 hasPrimaryLocation W29640596311 @default.
- W2964059631 hasRelatedWork W1489458588 @default.
- W2964059631 hasRelatedWork W1908253641 @default.
- W2964059631 hasRelatedWork W2004339613 @default.
- W2964059631 hasRelatedWork W2341066496 @default.
- W2964059631 hasRelatedWork W2552136414 @default.
- W2964059631 hasRelatedWork W2567844727 @default.
- W2964059631 hasRelatedWork W2573242115 @default.
- W2964059631 hasRelatedWork W2667760 @default.
- W2964059631 hasRelatedWork W2768727567 @default.
- W2964059631 hasRelatedWork W2783154620 @default.
- W2964059631 hasRelatedWork W2786479217 @default.
- W2964059631 hasRelatedWork W2904779604 @default.
- W2964059631 hasRelatedWork W2924879216 @default.
- W2964059631 hasRelatedWork W2972675484 @default.
- W2964059631 hasRelatedWork W2997630774 @default.
- W2964059631 hasRelatedWork W3037978882 @default.
- W2964059631 hasRelatedWork W3120436098 @default.
- W2964059631 hasRelatedWork W3121228496 @default.
- W2964059631 hasRelatedWork W3123699986 @default.
- W2964059631 hasRelatedWork W3185742958 @default.
- W2964059631 isParatext "false" @default.
- W2964059631 isRetracted "false" @default.
- W2964059631 magId "2964059631" @default.
- W2964059631 workType "article" @default.