COMPUTER, METHOD, AND COMPUTER PROGRAM LEARNING TO DETERMINE MULTIPLE OPERATION CONDITIONS OF ANIMAL AND PLANT RAISING DEVICE

To provide computers, animal and plant raising devices, methods, computer programs, and storage media that realize further efficient animal and plant raising, by enabling machine learning to select the operation conditions of an animal and plant raising device.SOLUTION: A system having an animal and plant raising device and a server device that learns multiple operation conditions of the animal and plant raising device comprises: a physical quantity acquisition unit that acquires the physical quantities of animals and plants raised based on the multiple operation conditions of the animal and plant raising device; a reward calculation unit that calculates the reward value related to at least one operation condition of the animal and plant raising device, based on the physical quantity; and a learning unit that learns an appropriate operation condition of the animal and plant raising device based on the reward value, by repeating the operations of the physical quantity acquisition unit and the reward calculation unit.SELECTED DRAWING: Figure 3 【課題】動植物育成装置稼動条件の選択を機械学習が行えるようにすることによって、動植物育成をより効率的に実現するコンピュータ、動植物育成装置、方法、コンピュータプログラムおよび記憶媒体を提供する。【解決手段】動植物育成装置と、複数の動植物育成装置稼動条件を学習するサーバ装置とを有するシステムにおいて、複数の動植物育成装置稼働条件に基づいて育てた動植物の物理量を取得する物理量取得部と、物理量に基づいて、少なくとも一つの動植物育成装置稼働条件に関連する報酬値を計算する報酬計算部と、物理量取得部及び報酬計算部の動作を繰り返すことによって、報酬値に基づいて適切な動植物育成装置稼動条件を学習する学習部と、を備える。【選択図】図３