عنوان انگلیسی مقاله:
A reinforcement learning scheme for the equilibrium of the in-vehicle route choice problem based on congestion game
ترجمه فارسی عنوان مقاله:
یک طرح یادگیری تقویت کننده برای تعادل در مسئله انتخاب مسیر خودرو بر اساس بازی ازدحام
Sciencedirect - Elsevier - Applied Mathematics and Computation, 371 (2020) 124895. doi:10.1016/j.amc.2019.124895
Bo Zhou a , b , ∗, Qiankun Song a , Zhenjiang Zhao c , Tangzhi Liu b
In this paper, the Bush–Mosteller (B-M) reinforcement learning (RL) scheme is introduced to model the route choice behaviors of the travelers in traffic networks, who aim to seek the optimal travel routes that minimize their individual travel time. The optimal route choice strategy is presented by the Nash equilibrium of the congestion game. By construct- ing a novel potential function, the congestion game is transformed into the traffic assign- ment problem (TAP). Then, a distributed algorithm based on B-M RL scheme is devised to solve the TAP. Under some mild conditions, the B-M RL solution method is proven to converge almost surely to the optimal solution of the TAP. A numerical experiment is con- ducted based on the Nguyen–Dupuis network, the experimental results not only demon- strate the effectiveness of the theoretical analysis, but also show that the B-M RL-based solution method outperforms several existing solution methods.
Keywords: Route choice problem | Congestion game | Nash equilibrium | Reinforcement learning | Learning automaton