摘要 |
<p>The invention provides a novel highly-adaptive agent learning machine comprising a plurality of learning modules (3), each having a set of a reinforcement learning system (1) which works on an environment (4), and determines an action output for maximizing a reward provided as a result thereof, and an environment predicting system (2), which predicts a change in the environment, wherein a responsibility signal is calculated such that the smaller a prediction error of the environment predicting system (2) of each of the learning modules (3), the larger the value thereof, and the action output by the reinforcement learning system (1) is weighted in proportion to the responsibility signal, thereby providing an action with regard to the environment. The machine switches and combines actions optimum to various states or operational modes of an environment without using any specific teacher signal, and performs behaviour learning flexibly, without using any prior knowledge. <IMAGE></p> |