@article{oai:nagoya.repo.nii.ac.jp:00005325,
 author = {Mukai, Naoto and Watanabe, Toyohide},
 journal = {17th IEEE International Conference on Tools with Artificial Intelligence},
 month = {Nov},
 note = {Route planning is one of the important tasks for transport systems. Appropriate policies  for route selections improve not only profitability of transport companies but also convenience of customers. Traditional ways for establishing the policies depend on manual efforts based on statistical data of transports. Moreover, traditional route planning techniques are reactive, i.e., an optimization based on information provided in advance. It is difficult for the manual policies and the reactive planning techniques to adjust dynamic changes of transport trends for customers such as amount and direction of transport demands, i.e., drivers of transport vehicles must follow the policies provided in advance. Therefore, in this paper we show how the proactive route planning based on expected rewards for transport systems can be modeled as a reinforcement learning problem. And, we show how agents as transport vehicles acquire their policies for route selection autonomously and dynamically. The leaning ability of transport trends enables transport vehicles to foresee the next destination which provides high rewards. Finally, we report simulation results and make the effectiveness of our proposal strategy clear.},
 pages = {51--57},
 title = {Proactive Route Planning Based on Expected Rewards for Transport Systems},
 year = {2005}
}