Application of stochastic learning automata for modeling departure time and route choice behavior
Stochastic learning automata (SLA) theory is used to model the learning behavior of commuters within the context of the combined departure time route choice (CDTRC) problem. The SLA model uses a reinforcement scheme to model the learning behavior of drivers. A multiaction linear reward-ε-penalty reinforcement scheme was introduced to model the learning behavior of travelers based on past departure time choice and route choice. A traffic simulation was developed to test the model. The results of the simulation are intended to show that drivers learn the best CDTRC option, and the network achieves user equilibrium in the long run. Results indicate that the developed SLA model accurately portrays the learning behavior of drivers, while the network satisfies user equilibrium conditions.
Automobile drivers; Commuters; Learning models (Stochastic processes); Traffic engineering; Traffic flow; Travel time (Traffic engineering)
Controls and Control Theory | Databases and Information Systems | Theory and Algorithms | Transportation | Urban Studies and Planning
Use Find in Your Library, contact the author, or use interlibrary loan to garner a copy of the article. Publisher copyright policy allows author to archive post-print (author’s final manuscript). When post-print is available or publisher policy changes, the article will be deposited
Ozbay, Kaan, Aleek Datta, and Pushkin Kachroo. "Application of stochastic learning automata for modeling departure time and route choice behavior." Transportation Research Record: Journal of the Transportation Research Board 1807, no. -1 (2002): 154-162.
Application of stochastic learning automata for modeling departure time and route choice behavior.
Transportation Research Record: Journal of the Transportation Research Board(1807),