@article{oai:fun.repo.nii.ac.jp:00005231,
 author = {Wakahara, Takumi and MIKAMI, Sadayoshi},
 issue = {7},
 journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
 month = {Sep},
 note = {An adaptive nutrient control method for a plant factory  is proposed. The method is based on a Reinforcement  Learning modified for a target in which one state  never comes back during a single episode and a reward  is given after a very long delay. In application such  as plant growth control, one episode takes a very long  time period, and a rapid convergence to a prospective  control solution is essential, whilst an extensive  exploration is needed since there is usually no precise  model available. A method like Reinforcement Learning  is useful for a problem having no reference model.  But a necesity of exploration does not match the need  for rapid convergence, and a new balancing method is  needed. In this research, an avarage reward distribution  method is proposed, which is similar to the Profit  Sharing method but affects more extensively to find  much prospective early solutions, whilst guaranteeing  to converge into a rational solution in a long run. An  experiment is conducted in a simple plant factory system,  which shows that at least standard Reinforcement  Learning is insufficient for this type of problem. Computer  simulations show that the method has good effects  comparing to a standard RL, and a profit sharing  method., doi: 10.20965/jaciii.2011.p0831},
 pages = {831--837},
 title = {Adaptive Nutrient Water Supply Control of Plant Factory System by Reinforcement Learning},
 volume = {15},
 year = {2011}
}