Markov decision process routing games

We explore an extension of nonatomic routing games that we call Markov decision process routing games where each agent chooses a transition policy between nodes in a network rather than a path from an origin node to a destination node, i.e. each agent in the population solves a Markov decision proce...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2017 ACM IEEE 8th International Conference on Cyber Physical Systems (ICCPS) s. 273 - 279
Hlavní autoři:	Calderone, Dan, Sastry, S. Shankar
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	New York, NY, USA ACM 18.04.2017
Edice:	ACM Other Conferences
Témata:	anonymous sequential games Computing methodologies > Machine learning > Machine learning approaches > Stochastic games Games Markov decision processes Markov processes mean-field games Networks > Network algorithms > Control path algorithms > Traffic engineering algorithms Rats Routing routing games Sociology Statistics Stochastic games Theory of computation > Theory and algorithms for application domains > Algorithmic game theory and mechanism design > Network games Theory of computation > Theory and algorithms for application domains > Machine learning theory > Markov decision processes routing games Markov decision processes anonymous sequential games mean-field games stochastic games
ISBN:	9781450349659, 145034965X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	We explore an extension of nonatomic routing games that we call Markov decision process routing games where each agent chooses a transition policy between nodes in a network rather than a path from an origin node to a destination node, i.e. each agent in the population solves a Markov decision process rather than a shortest path problem. We define the appropriate version of a Wardrop equilibrium as well as a potential function for this game in the finite horizon (total reward) case. This work can be thought of as a routing-game-based formulation of continuous population stochastic games (mean-field games or anonymous sequential games). We apply our model to the problem of ridesharing drivers competing for customers.
ISBN:	9781450349659 145034965X
DOI:	10.1145/3055004.3055026